You Only Look Once: Unified, Real-Time Object Detection
Open accessAbstract
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
AI snapshot
Written from the paper’s full text.
TL;DR
YOLO reframes object detection as a single regression problem, using one convolutional network to predict bounding boxes and class probabilities directly from full images. It achieves real-time detection speeds while remaining competitive with, and complementary to, slower region-based detectors.
Key findings
- YOLO runs at 45 FPS on a Titan X GPU, and Fast YOLO runs at 155 FPS; Fast YOLO reaches 52.7% mAP on PASCAL VOC 2007, more than double prior real-time detectors, while YOLO reaches 63.4% mAP.
- On PASCAL VOC 2012, YOLO scores 57.9% mAP; combining Fast R-CNN with YOLO raises Fast R-CNN from 71.8% to 75.0% mAP on VOC 2007, a 3.2% gain.
- YOLO makes fewer background false positives than Fast R-CNN: Fast R-CNN has 13.6% background false positives among top detections and is almost 3× more likely to predict background detections than YOLO.
- YOLO generalizes better to artwork: on Picasso, YOLO gets 53.3 AP versus R-CNN’s 10.4 AP and DPM’s 37.8 AP; on People-Art, YOLO gets 45 AP versus R-CNN’s 26 AP and DPM’s 32 AP.
Methods
- Detection is modeled as a single CNN regression: the image is divided into an S×S grid; for PASCAL VOC, S=7, B=2, C=20, producing a 7×7×30 tensor of bounding boxes, confidence scores, and class probabilities.
- The base network has 24 convolutional layers followed by 2 fully connected layers; Fast YOLO uses 9 convolutional layers. Convolutional layers are pretrained on ImageNet at 224×224, then detection training uses 448×448 input.
- Training uses PASCAL VOC 2007 and 2012 for about 135 epochs, batch size 64, momentum 0.9, decay 0.0005, sum-squared error with λ_coord=5 and λ_noobj=0.5, dropout, and data augmentation.
Limitations
- The paper states YOLO imposes strong spatial constraints because each grid cell predicts only two boxes and one class, limiting nearby objects and struggling with small objects in groups such as flocks of birds.
- The paper states YOLO struggles to generalize to objects in new or unusual aspect ratios or configurations, uses relatively coarse features due to downsampling, and its loss treats small and large box errors equally; its main error source is incorrect localization.
- The paper states YOLO still lags state-of-the-art detection accuracy and struggles to precisely localize some objects, especially small ones.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
7 of 25 cited sources checked · 2 supported · 0 flagged · accuracy not yet measured
- Premisecitation§ 4.1. Comparison to Other Real-Time Systems · p. 5
R-CNN minus R falls short of real-time.
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
Quote in the paperSubstantial claim1 of 1 sources checked- cites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - source
The ConvNet-based Object Detection section identifies R-CNN minus R as a method that uses predefined regions instead of region proposals. It gives no runtime measurement or assessment of whether the method achieves real-time detection; searches for real-time performance and speed did not establish that claim. (LLM, conf=0.76)
Experimental — accuracy not yet measured
- Study design and conductcitation§ 2.2. Training · p. 4
To avoid overfitting, YOLO uses dropout and extensive data augmentation.
“To avoid overfitting we use dropout and extensive data augmentation.”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites [18] [18] G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 , 2012. 4 - source
The paper states that dropout reduces overfitting (p. 1) and describes using dropout with data augmentation for its ImageNet model (H Models for ImageNet, p. 18). It does not establish that YOLO uses either technique or describe YOLO’s augmentation as extensive. (LLM, conf=0.88)
Experimental — accuracy not yet measured
- Premisecitation§ 4.1. Comparison to Other Real-Time Systems · p. 5
R-CNN minus R is much faster than R-CNN.
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - source
The ConvNet-based Object Detection section identifies R-CNN minus R and says it uses predefined regions in an SPPnet system, but gives no speed comparison with R-CNN. A search for R-CNN minus R and speed found no passage in our copy establishing that it is much faster. (LLM, conf=0.73)
Experimental — accuracy not yet measured
- Premisecitation§ 4.1. Comparison to Other Real-Time Systems · p. 5
R-CNN minus R takes a significant accuracy hit from not having good proposals.
“While it is much faster than R-CNN, it still falls short of real-time and takes a significant accuracy hit from not having good proposals.”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - source
The “ConvNet-based Object Detection” section (page unavailable) says R-CNN minus R uses predefined regions instead of region proposals. It does not say that this causes a significant accuracy loss; the paper’s discussion of low accuracy concerns a different system, naïve Faster R-CNN. (LLM, conf=0.83)
Experimental — accuracy not yet measured
- Findingown data§ 4.4. VOC 2012 Results · p. 7
YOLO struggles with small objects compared to its closest competitors.
“Our system struggles with small objects compared to its closest competitors.”
Quote in the paperNot a substantial claim
- Findingreasoning§ 4.5. Generalizability: Person Detection in Artwork · p. 7
YOLO's AP degrades less than other methods when applied to artwork.
“YOLO has good performance on VOC 2007 and its AP degrades less than other methods when applied to artwork.”
Quote in the paperNot a substantial claim - Findingreasoning§ 4.5. Generalizability: Person Detection in Artwork · p. 7
R-CNN drops off considerably when applied to artwork.
“However, R-CNN drops off considerably when applied to artwork.”
Quote in the paperSubstantial claim - Findingreasoning§ 1. Introduction · p. 2
YOLO struggles to precisely localize some objects, especially small ones.
“While it can quickly identify objects in images it struggles to precisely localize some objects, especially small ones.”
- Also stated in: § 2.4. Limitations of YOLO · p. 4 · plain
“Our model struggles with small objects that appear in groups, such as flocks of birds.”
Quote in the paperNot a substantial claim - Also stated in: § 2.4. Limitations of YOLO · p. 4 · plain
- Findingnone given§ You Only Look Once: Unified, Real-Time Object Detection · p. 1
YOLO achieves more than twice the mean average precision of other real-time systems.
“Furthermore, YOLO achieves more than twice the mean average precision of other real-time systems.”
Quote in the paperNot a substantial claim - Findingnone given§ 2.4. Limitations of YOLO · p. 4
YOLO's main source of error is incorrect localizations.
“Our main source of error is incorrect localizations.”
Quote in the paperNot a substantial claim - Findingown data§ 4.2. VOC 2007 Error Analysis · p. 6
Localization errors account for more of YOLO's errors than all other sources combined.
“Localization errors account for more of YOLO's errors than all other sources combined.”
Quote in the paperNot a substantial claim - Findingown data§ 4.2. VOC 2007 Error Analysis · p. 6
13.6% of Fast R-CNN's top detections are false positives that don't contain any objects.
“13.6% of it's top detections are false positives that don't contain any objects.”
Quote in the paperNot a substantial claim - Findingreasoning§ 4.5. Generalizability: Person Detection in Artwork · p. 7
DPM maintains its AP well when applied to artwork.
“DPM maintains its AP well when applied to artwork.”
Quote in the paperNot a substantial claim - Findingown data§ Abstract · p. 1
YOLO's base model processes images in real-time at 45 frames per second.
“Our base YOLO model processes images in real-time at 45 frames per second.”
- Also stated in: § You Only Look Once: Unified, Real-Time Object Detection · p. 1 · plain
“Our base network runs at 45 frames per second with no batch processing on a Titan X GPU”
Quote in the paperSubstantial claim - Also stated in: § You Only Look Once: Unified, Real-Time Object Detection · p. 1 · plain
- Findingown data§ Abstract · p. 1
Fast YOLO achieves double the mAP of other real-time detectors.
“while still achieving double the mAP of other real-time detectors.”
- Also stated in: § 4.1. Comparison to Other Real-Time Systems · p. 5 · plain
“With 52 . 7% mAP, it is more than twice as accurate as prior work on real-time detection.”
Quote in the paperSubstantial claim - Also stated in: § 4.1. Comparison to Other Real-Time Systems · p. 5 · plain
- Findingown data§ Abstract · p. 1
Fast YOLO processes 155 frames per second.
“A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second”
- Also stated in: § You Only Look Once: Unified, Real-Time Object Detection · p. 1 · plain
“a fast version runs at more than 150 fps”
Quote in the paperSubstantial claim - Also stated in: § You Only Look Once: Unified, Real-Time Object Detection · p. 1 · plain
- Findingreasoning§ Abstract · p. 1
Compared to state-of-the-art detection systems, YOLO is less likely to predict false positives on background.
“but is less likely to predict false positives on background.”
- Also stated in: § 1. Introduction · p. 1 · plain
“YOLO makes less than half the number of background errors compared to Fast R-CNN.”
Quote in the paperSubstantial claim - Also stated in: § 1. Introduction · p. 1 · plain
- Findingnone given§ Abstract · p. 1
Compared to state-of-the-art detection systems, YOLO makes more localization errors.
“Compared to state-of-the-art detection systems, YOLO makes more localization errors”
Quote in the paperNot a substantial claim - Findingown data§ Abstract · p. 1
YOLO outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
“It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.”
- Also stated in: § 1. Introduction · p. 2 · boosted
“When trained on natural images and tested on artwork, YOLO outperforms top detection methods like DPM and R-CNN by a wide margin.”
Quote in the paperSubstantial claim - Also stated in: § 1. Introduction · p. 2 · boosted
- Findingown data§ 2.3. Inference · p. 4
YOLO predicts 98 bounding boxes per image on PASCAL VOC.
“On PASCAL VOC the network predicts 98 bounding boxes per image and class probabilities for each box.”
- Also stated in: § 3. Comparison to Other Detection Systems · p. 5 · plain
“Our system also proposes far fewer bounding boxes, only 98 per image compared to about 2000 from Selective Search.”
Quote in the paperSubstantial claim - Also stated in: § 3. Comparison to Other Detection Systems · p. 5 · plain
- Findingown data§ 4.1. Comparison to Other Real-Time Systems · p. 6
YOLO is 10 mAP more accurate than Fast YOLO.
“YOLO is 10 mAP more accurate than the fast version while still well above real-time in speed.”
Quote in the paperSubstantial claim - Findingown data§ 2.2. Training · p. 3
YOLO pretraining achieves 88% single crop top-5 accuracy on the ImageNet 2012 validation set.
“We train this network for approximately a week and achieve a single crop top-5 accuracy of 88% on the ImageNet 2012 validation set”
Quote in the paperNot a substantial claim - Findingreasoning§ 1. Introduction · p. 1
YOLO makes less than half the number of background errors compared to Fast R-CNN.
“YOLO makes less than half the number of background errors compared to Fast R-CNN.”
Quote in the paperNot a substantial claim - Findingown data§ 4.1. Comparison to Other Real-Time Systems · p. 6
Fast YOLO is the fastest detector on record for PASCAL VOC detection.
“Fast YOLO is the fastest detector on record for PASCAL VOC detection and is still twice as accurate as any other real-time detector.”
Quote in the paperSubstantial claim - Findingown data§ 4.1. Comparison to Other Real-Time Systems · p. 6
YOLO is still well above real-time in speed.
“YOLO is 10 mAP more accurate than the fast version while still well above real-time in speed.”
Quote in the paperSubstantial claim - Findingown data§ 4.1. Comparison to Other Real-Time Systems · p. 5
Fast YOLO achieves 52.7% mAP.
“With 52 . 7% mAP, it is more than twice as accurate as prior work on real-time detection.”
Quote in the paperSubstantial claim - Findingown data§ 4.1. Comparison to Other Real-Time Systems · p. 6
Fast YOLO is still twice as accurate as any other real-time detector.
“Fast YOLO is the fastest detector on record for PASCAL VOC detection and is still twice as accurate as any other real-time detector.”
Quote in the paperSubstantial claim - Findingown data§ 4.4. VOC 2012 Results · p. 7
The combination boosts Fast R-CNN 5 spots up on the public leaderboard.
“Fast R-CNN gets a 2.3% improvement from the combination with YOLO, boosting it 5 spots up on the public leaderboard.”
Quote in the paperNot a substantial claim - Findingreasoning§ 4.1. Comparison to Other Real-Time Systems · p. 6
Fast R-CNN runs at 0.5 fps.
“Thus it has high mAP but at 0 . 5 fps it is still far from realtime.”
Quote in the paperSubstantial claim - Findingown data§ 4.1. Comparison to Other Real-Time Systems · p. 6
The ZeilerFergus Faster R-CNN is 2.5 times slower than YOLO.
“The ZeilerFergus Faster R-CNN is only 2.5 times slower than YOLO but is also less accurate.”
Quote in the paperNot a substantial claim - Findingown data§ 4.1. Comparison to Other Real-Time Systems · p. 6
In our tests, Faster R-CNN's most accurate model achieves 7 fps.
“In our tests, their most accurate model achieves 7 fps while a smaller, less accurate one runs at 18 fps.”
Quote in the paperSubstantial claim - Findingnone given§ 4.5. Generalizability: Person Detection in Artwork · p. 7
YOLO has good performance on VOC 2007.
“YOLO has good performance on VOC 2007 and its AP degrades less than other methods when applied to artwork.”
Quote in the paperNot a substantial claim - Findingown data§ 4.2. VOC 2007 Error Analysis · p. 6
Fast R-CNN is almost 3x more likely to predict background detections than YOLO.
“Fast R-CNN is almost 3x more likely to predict background detections than YOLO.”
Quote in the paperNot a substantial claim - Findingown data§ 4.2. VOC 2007 Error Analysis · p. 6
YOLO struggles to localize objects correctly.
“YOLO struggles to localize objects correctly.”
Quote in the paperNot a substantial claim - Findingown data§ 4.4. VOC 2012 Results · p. 7
YOLO scores 57.9% mAP on VOC 2012 test set.
“On the VOC 2012 test set, YOLO scores 57.9% mAP.”
Quote in the paperSubstantial claim - Findingown data§ 4.4. VOC 2012 Results · p. 7
On categories bottle, sheep, and tv/monitor, YOLO scores 8-10% lower than R-CNN or Feature Edit.
“On categories like bottle , sheep , and tv/monitor YOLO scores 8-10% lower than R-CNN or Feature Edit.”
Quote in the paperNot a substantial claim - Findingown data§ 4.1. Comparison to Other Real-Time Systems · p. 6
In our tests, a smaller, less accurate Faster R-CNN model runs at 18 fps.
“In our tests, their most accurate model achieves 7 fps while a smaller, less accurate one runs at 18 fps.”
Quote in the paperSubstantial claim - Findingown data§ 4.3. Combining Fast R-CNN and YOLO · p. 7
Fast R-CNN + YOLO improves Fast R-CNN by 2.3% mAP.
“Fast R-CNN + YOLO is the forth highest scoring method, with a 2.3% boost over Fast R-CNN.”
- Also stated in: § 4.4. VOC 2012 Results · p. 7 · plain
“Fast R-CNN gets a 2.3% improvement from the combination with YOLO, boosting it 5 spots up on the public leaderboard.”
Quote in the paperNot a substantial claim - Also stated in: § 4.4. VOC 2012 Results · p. 7 · plain
- Findingown data§ 4.1. Comparison to Other Real-Time Systems · p. 6
The VGG-16 version of Faster R-CNN is 6 times slower than YOLO.
“The VGG-16 version of Faster R-CNN is 10 mAP higher but is also 6 times slower than YOLO.”
Quote in the paperSubstantial claim - Findingown data§ 4.3. Combining Fast R-CNN and YOLO · p. 7
YOLO is the only real-time detector on the PASCAL VOC 2012 leaderboard.
“YOLO is the only real-time detector.”
Quote in the paperSubstantial claim - Findingreasoning§ 4.3. Combining Fast R-CNN and YOLO · p. 6
Using YOLO to eliminate background detections from Fast R-CNN significantly boosts performance.
“By using YOLO to eliminate background detections from Fast R-CNN we get a significant boost in performance.”
- Also stated in: § 4.3. Combining Fast R-CNN and YOLO · p. 6 · plain
“Other versions of Fast R-CNN provide only a small benefit while YOLO provides a significant performance boost.”
Quote in the paperSubstantial claim - Also stated in: § 4.3. Combining Fast R-CNN and YOLO · p. 6 · plain
- Findingown data§ 4.3. Combining Fast R-CNN and YOLO · p. 6
When combined with YOLO, the best Fast R-CNN model's mAP increases by 3.2% to 75.0%.
“When combined with YOLO, its mAP increases by 3.2% to 75.0%.”
Quote in the paperSubstantial claim - Findingown data§ 4.2. VOC 2007 Error Analysis · p. 6
Fast R-CNN makes much fewer localization errors than YOLO.
“Fast R-CNN makes much fewer localization errors but far more background errors.”
Quote in the paperNot a substantial claim - Findingreasoning§ 4.5. Generalizability: Person Detection in Artwork · p. 7
DPM doesn't degrade as much as R-CNN when applied to artwork.
“Though DPM doesn't degrade as much as R-CNN, it starts from a lower AP.”
Quote in the paperNot a substantial claim - Findingnone given§ 4.5. Generalizability: Person Detection in Artwork · p. 7
DPM starts from a lower AP than R-CNN.
“Though DPM doesn't degrade as much as R-CNN, it starts from a lower AP.”
Quote in the paperNot a substantial claim - Findingown data§ 4.3. Combining Fast R-CNN and YOLO · p. 6
The best Fast R-CNN model achieves 71.8% mAP on the VOC 2007 test set.
“The best Fast R-CNN model achieves a mAP of 71.8% on the VOC 2007 test set.”
Quote in the paperSubstantial claim - Findingown data§ 4.3. Combining Fast R-CNN and YOLO · p. 7
Fast R-CNN + YOLO is the fourth highest scoring method on the PASCAL VOC 2012 leaderboard.
“Fast R-CNN + YOLO is the forth highest scoring method, with a 2.3% boost over Fast R-CNN.”
Quote in the paperNot a substantial claim - Findingown data§ 4.3. Combining Fast R-CNN and YOLO · p. 6
Combining the top Fast R-CNN model with other versions of Fast R-CNN provides only small increases in mAP (0.3-0.6%).
“Those ensembles produced small increases in mAP between .3 and .6%, see Table 2 for details.”
- Also stated in: § 4.3. Combining Fast R-CNN and YOLO · p. 6 · plain
“Other versions of Fast R-CNN provide only a small benefit while YOLO provides a significant performance boost.”
Quote in the paperSubstantial claim - Also stated in: § 4.3. Combining Fast R-CNN and YOLO · p. 6 · plain
- Findingown data§ 4.2. VOC 2007 Error Analysis · p. 6
Fast R-CNN makes far more background errors than YOLO.
“Fast R-CNN makes much fewer localization errors but far more background errors.”
- Also stated in: § 4.3. Combining Fast R-CNN and YOLO · p. 6 · plain
“YOLO makes far fewer background mistakes than Fast R-CNN.”
Quote in the paperSubstantial claim - Also stated in: § 4.3. Combining Fast R-CNN and YOLO · p. 6 · plain
- Findingreasoning§ 4.1. Comparison to Other Real-Time Systems · p. 6
Fast R-CNN has high mAP.
“Thus it has high mAP but at 0 . 5 fps it is still far from realtime.”
Quote in the paperNot a substantial claim - Findingown data§ 4.4. VOC 2012 Results · p. 7
On categories cat and train, YOLO achieves higher performance than R-CNN or Feature Edit.
“However, on other categories like cat and train YOLO achieves higher performance.”
Quote in the paperNot a substantial claim - Findingown data§ 4.1. Comparison to Other Real-Time Systems · p. 6
The ZeilerFergus Faster R-CNN is less accurate than YOLO.
“The ZeilerFergus Faster R-CNN is only 2.5 times slower than YOLO but is also less accurate.”
Quote in the paperNot a substantial claim - Findingown data§ 4.1. Comparison to Other Real-Time Systems · p. 6
The VGG-16 version of Faster R-CNN is 10 mAP higher than YOLO.
“The VGG-16 version of Faster R-CNN is 10 mAP higher but is also 6 times slower than YOLO.”
Quote in the paperNot a substantial claim - Interpretationreasoning§ 4.3. Combining Fast R-CNN and YOLO · p. 7
YOLO is effective at boosting Fast R-CNN's performance precisely because YOLO makes different kinds of mistakes at test time.
“Rather, it is precisely because YOLO makes different kinds of mistakes at test time that it is so effective at boosting Fast R-CNN's performance.”
Quote in the paperSubstantial claim - Interpretationown data§ 4.3. Combining Fast R-CNN and YOLO · p. 7
The boost from YOLO is not simply a byproduct of model ensembling.
“The boost from YOLO is not simply a byproduct of model ensembling since there is little benefit from combining different versions of Fast R-CNN.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 1. Introduction · p. 1
YOLO sees the entire image during training and test time so it implicitly encodes contextual information about classes as well as their appearance.
“Unlike sliding window and region proposal-based techniques, YOLO sees the entire image during training and test time so it implicitly encodes contextual information about classes as well as their appearance.”
Quote in the paperSubstantial claim - Interpretationreasoning§ You Only Look Once: Unified, Real-Time Object Detection · p. 1
YOLO can process streaming video in real-time with less than 25 milliseconds of latency.
“This means we can process streaming video in real-time with less than 25 milliseconds of latency.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 6. Conclusion · p. 8
YOLO pushes the state-of-the-art in real-time object detection.
“Fast YOLO is the fastest general-purpose object detector in the literature and YOLO pushes the state-of-the-art in real-time object detection.”
Quote in the paperSubstantial claim - Interpretationreasoning§ Abstract · p. 1
A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation.
“A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation.”
- Also stated in: § 2. Unified Detection · p. 2 · plain
“Our network uses features from the entire image to predict each bounding box.”
Quote in the paperSubstantial claim - Also stated in: § 2. Unified Detection · p. 2 · plain
- Interpretationreasoning§ Abstract · p. 1
Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance.
“Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance.”
Quote in the paperSubstantial claim - Interpretationnone given§ Abstract · p. 1
YOLO frames object detection as a single regression problem from image pixels to bounding box coordinates and class probabilities.
“Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities.”
- Also stated in: § You Only Look Once: Unified, Real-Time Object Detection · p. 1 · plain
“We reframe object detection as a single regression problem, straight from image pixels to bounding box coordinates and class probabilities.”
Quote in the paperSubstantial claim - Also stated in: § You Only Look Once: Unified, Real-Time Object Detection · p. 1 · plain
- Premisecitation§ 4.1. Comparison to Other Real-Time Systems · p. 6
Fast R-CNN speeds up the classification stage of R-CNN.
“Fast R-CNN speeds up the classification stage of R-CNN but it still relies on selective search which can take around 2 seconds per image to generate bounding box proposals.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [14] [14] R. B. Girshick. Fast R-CNN. CoRR , abs/1504.08083, 2015. 2, 5, 6, 7 - source
- Interpretationnone given§ 2.2. Training · p. 3
Assigning one predictor responsible based on highest current IOU leads to specialization between bounding box predictors.
“We assign one predictor to be 'responsible' for predicting an object based on which prediction has the highest current IOU with the ground truth. This leads to specialization between the bounding box predictors.”
Quote in the paperSubstantial claim - Interpretationnone given§ 3. Comparison to Other Detection Systems · p. 5
YOLO combines individual components into a single, jointly optimized model.
“Finally, our system combines these individual components into a single, jointly optimized model.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 2.2. Training · p. 3
YOLO's sum-squared error does not perfectly align with the goal of maximizing average precision.
“We use sum-squared error because it is easy to optimize, however it does not perfectly align with our goal of maximizing average precision.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 2.4. Limitations of YOLO · p. 4
YOLO struggles to generalize to objects in new or unusual aspect ratios or configurations because it learns to predict bounding boxes from data.
“Since our model learns to predict bounding boxes from data, it struggles to generalize to objects in new or unusual aspect ratios or configurations.”
Quote in the paperNot a substantial claim - Interpretationnone given§ 2.3. Inference · p. 4
The grid design enforces spatial diversity in the bounding box predictions.
“The grid design enforces spatial diversity in the bounding box predictions.”
Quote in the paperNot a substantial claim - Interpretationreasoning§ 1. Introduction · p. 2
YOLO is less likely to break down when applied to new domains or unexpected inputs because it is highly generalizable.
“Since YOLO is highly generalizable it is less likely to break down when applied to new domains or unexpected inputs.”
Quote in the paperSubstantial claim - Premisecitation§ 3. Comparison to Other Detection Systems · p. 5
Only 30Hz DPM actually runs in real-time among many research efforts to speed up DPM.
“However, only 30Hz DPM [31] actually runs in real-time.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [31] [31] M. A. Sadeghi and D. Forsyth. 30hz object detection with dpm v5. In Computer Vision-ECCV 2014 , pages 65-79. Springer, 2014. 5, 6 - source
- Interpretationnone given§ 3. Comparison to Other Detection Systems · p. 5
YOLO puts spatial constraints on grid cell proposals which helps mitigate multiple detections of the same object.
“However, our system puts spatial constraints on the grid cell proposals which helps mitigate multiple detections of the same object.”
Quote in the paperNot a substantial claim - Interpretationreasoning§ 2.2. Training · p. 3
Sum-squared error weights localization error equally with classification error, which may not be ideal.
“It weights localization error equally with classification error which may not be ideal.”
Quote in the paperNot a substantial claim - Premisecitation§ 3. Comparison to Other Detection Systems · p. 5
Fast and Faster R-CNN still fall short of real-time performance.
“While they offer speed and accuracy improvements over R-CNN, both still fall short of real-time performance.”
Quote in the paperSubstantial claim0 of 2 sources checked - Interpretationreasoning§ 2.4. Limitations of YOLO · p. 4
YOLO uses relatively coarse features for predicting bounding boxes because its architecture has multiple downsampling layers from the input image.
“Our model also uses relatively coarse features for predicting bounding boxes since our architecture has multiple downsampling layers from the input image.”
Quote in the paperNot a substantial claim - Interpretationown data§ Abstract · p. 1
YOLO learns very general representations of objects.
“Finally, YOLO learns very general representations of objects.”
- Also stated in: § 1. Introduction · p. 2 · plain
“Third, YOLO learns generalizable representations of objects.”
Quote in the paperSubstantial claim - Also stated in: § 1. Introduction · p. 2 · plain
- Premisecitation§ 3. Comparison to Other Detection Systems · p. 4
The R-CNN pipeline is very slow, taking more than 40 seconds per image at test time.
“Each stage of this complex pipeline must be precisely tuned independently and the resulting system is very slow, taking more than 40 seconds per image at test time [14].”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [14] [14] R. B. Girshick. Fast R-CNN. CoRR , abs/1504.08083, 2015. 2, 5, 6, 7 - source
- Interpretationreasoning§ 2.4. Limitations of YOLO · p. 4
The spatial constraint limits the number of nearby objects that YOLO can predict.
“This spatial constraint limits the number of nearby objects that our model can predict.”
Quote in the paperNot a substantial claim - Interpretationnone given§ 2.4. Limitations of YOLO · p. 4
YOLO's loss function treats errors the same in small bounding boxes versus large bounding boxes.
“our loss function treats errors the same in small bounding boxes versus large bounding boxes.”
Quote in the paperSubstantial claim - Premisecitation§ 4.1. Comparison to Other Real-Time Systems · p. 6
Selective search can take around 2 seconds per image to generate bounding box proposals.
“Fast R-CNN speeds up the classification stage of R-CNN but it still relies on selective search which can take around 2 seconds per image to generate bounding box proposals.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [14] [14] R. B. Girshick. Fast R-CNN. CoRR , abs/1504.08083, 2015. 2, 5, 6, 7 - source
- Premisereasoning§ 6. Conclusion · p. 8
The entire YOLO model is trained jointly.
“Unlike classifier-based approaches, YOLOis trained on a loss function that directly corresponds to detection performance and the entire model is trained jointly.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 4.3. Combining Fast R-CNN and YOLO · p. 7
YOLO does not add significant computational time compared to Fast R-CNN when combined.
“However, since YOLO is so fast it doesn't add any significant computational time compared to Fast R-CNN.”
Quote in the paperNot a substantial claim - Premisenone given§ 6. Conclusion · p. 8
YOLO is a unified model for object detection.
“We introduce YOLO, a unified model for object detection.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 4.1. Comparison to Other Real-Time Systems · p. 6
Fast R-CNN is far from realtime.
“Thus it has high mAP but at 0 . 5 fps it is still far from realtime.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 4.3. Combining Fast R-CNN and YOLO · p. 7
The Fast R-CNN + YOLO combination does not benefit from YOLO's speed because the models are run separately and then combined.
“Unfortunately, this combination doesn't benefit from the speed of YOLO since we run each model seperately and then combine the results.”
Quote in the paperNot a substantial claim - Interpretationreasoning§ 4.5. Generalizability: Person Detection in Artwork · p. 7
YOLO can still predict good bounding boxes and detections on artwork because artwork and natural images are similar in terms of the size and shape of objects.
“Artwork and natural images are very different on a pixel level but they are similar in terms of the size and shape of objects, thus YOLO can still predict good bounding boxes and detections.”
Quote in the paperSubstantial claim- Rests on an assumption: Artwork and natural images are similar in terms of the size and shape of objects.
- Interpretationown data§ 4.4. VOC 2012 Results · p. 7
Combined Fast R-CNN + YOLO is one of the highest performing detection methods.
“Our combined Fast R-CNN + YOLO model is one of the highest performing detection methods.”
Quote in the paperNot a substantial claim - Premisenone given§ 6. Conclusion · p. 8
YOLO can be trained directly on full images.
“Our model is simple to construct and can be trained directly on full images.”
Quote in the paperSubstantial claim - Premisecitation§ 4.5. Generalizability: Person Detection in Artwork · p. 7
In real-world applications, test data can diverge from what the system has seen before.
“In real-world applications it is hard to predict all possible use cases and the test data can diverge from what the system has seen before [3].”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [3] [3] H. Cai, Q. Wu, T. Corradi, and P. Hall. The crossdepiction problem: Computer vision algorithms for recognising objects in artwork and in photographs. arXiv preprint arXiv:1505.00110 , 2015. 7 - source
- Premisecitation§ 4.1. Comparison to Other Real-Time Systems · p. 6
Fast R-CNN still relies on selective search.
“Fast R-CNN speeds up the classification stage of R-CNN but it still relies on selective search which can take around 2 seconds per image to generate bounding box proposals.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [14] [14] R. B. Girshick. Fast R-CNN. CoRR , abs/1504.08083, 2015. 2, 5, 6, 7 - source
- Premisenone given§ 6. Conclusion · p. 8
Unlike classifier-based approaches, YOLO is trained on a loss function that directly corresponds to detection performance.
“Unlike classifier-based approaches, YOLOis trained on a loss function that directly corresponds to detection performance and the entire model is trained jointly.”
Quote in the paperSubstantial claim
- Classified as probably not a substantial claim. 17
- May combine two claims. 15
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 2.2. Training · p. 3Adding both convolutional and connected layers to pretrained networks can improve performance.
“Ren et al. show that adding both convolutional and connected layers to pretrained networks can improve performance [29].”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites [29] [29] S. Ren, K. He, R. B. Girshick, X. Zhang, and J. Sun. Object detection networks on convolutional feature maps. CoRR , abs/1504.06066, 2015. 3, 7 - source
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 4.1. Comparison to Other Real-Time Systems · p. 5R-CNN minus R replaces Selective Search with static bounding box proposals.
“R-CNN minus R replaces Selective Search with static bounding box proposals [20].”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - source
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 2.2. Training · p. 4A dropout layer with rate .5 after the first connected layer prevents co-adaptation between layers.
“A dropout layer with rate = .5 after the first connected layer prevents co-adaptation between layers [18].”
Quote in the paperNot a substantial claim1 of 1 sources checked- cites [18] [18] G. E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, and R. R. Salakhutdinov. Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580 , 2012. 4 - source
The main text (p. 1) says dropout omits hidden units with probability 0.5 to prevent complex co-adaptations. But the discussion of fully connected layers (p. 5) does not establish that placing one dropout layer after the first fully connected layer has that effect; it says dropout in all hidden layers works better than dropout in only one. (LLM, conf=0.87)
Experimental — accuracy not yet measured
May combine two claims.
Findingown data§ 4.4. VOC 2012 Results · p. 7YOLO's VOC 2012 mAP is lower than the current state of the art and closer to the original R-CNN using VGG-16.
“This is lower than the current state of the art, closer to the original R-CNN using VGG-16, see Table 3.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given§ 1. Introduction · p. 2YOLO still lags behind state-of-the-art detection systems in accuracy.
“YOLOstill lags behind state-of-the-art detection systems in accuracy.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given§ 2.3. Inference · p. 4Non-maximal suppression adds 23% in mAP.
“While not critical to performance as it is for R-CNN or DPM, non-maximal suppression adds 23% in mAP.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S4 (based).
Findingnone given§ 6. Conclusion · p. 8Fast YOLO is the fastest general-purpose object detector in the literature.
“Fast YOLO is the fastest general-purpose object detector in the literature and YOLO pushes the state-of-the-art in real-time object detection.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingreasoning§ 3. Comparison to Other Detection Systems · p. 4YOLO's unified architecture leads to a faster, more accurate model than DPM.
“Our unified architecture leads to a faster, more accurate model than DPM.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingreasoning§ 5. Real-Time Detection In The Wild · p. 8When attached to a webcam, YOLO functions like a tracking system, detecting objects as they move around and change in appearance.
“While YOLO processes images individually, when attached to a webcam it functions like a tracking system, detecting objects as they move around and change in appearance.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown data§ 4.1. Comparison to Other Real-Time Systems · p. 5YOLO trained using VGG-16 is more accurate but significantly slower than YOLO.
“We also train YOLO using VGG-16. This model is more accurate but also significantly slower than YOLO.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown data§ 4.1. Comparison to Other Real-Time Systems · p. 5YOLO achieves 63.4% mAP while maintaining real-time performance.
“YOLO pushes mAP to 63 . 4% while still maintaining real-time performance.”
Quote in the paperSubstantial claimMay combine two claims.
Findingown data§ 4.1. Comparison to Other Real-Time Systems · p. 5Fast YOLO is the fastest object detection method on PASCAL; as far as the authors know, it is the fastest extant object detector.
“Fast YOLO is the fastest object detection method on PASCAL; as far as we know, it is the fastest extant object detector.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Findingnone given§ 4.5. Generalizability: Person Detection in Artwork · p. 7R-CNN has high AP on VOC 2007.
“R-CNN has high AP on VOC 2007.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown data§ 5. Real-Time Detection In The Wild · p. 7YOLO is a fast, accurate object detector.
“YOLO is a fast, accurate object detector, making it ideal for computer vision applications.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S4 (based).
Findingnone given§ 6. Conclusion · p. 8YOLO generalizes well to new domains.
“YOLO also generalizes well to new domains making it ideal for applications that rely on fast, robust object detection.”
Quote in the paperNot a substantial claimMay combine two claims.
Interpretationreasoning§ 2. Unified Detection · p. 2The YOLO design enables end-to-end training and real-time speeds while maintaining high average precision.
“The YOLO design enables end-to-end training and realtime speeds while maintaining high average precision.”
Quote in the paperSubstantial claimMay combine two claims.
Interpretationreasoning§ 2.3. Inference · p. 4YOLO is extremely fast at test time since it only requires a single network evaluation, unlike classifier-based methods.
“YOLO is extremely fast at test time since it only requires a single network evaluation, unlike classifier-based methods.”
Quote in the paperSubstantial claimMay combine two claims.
Premisereasoning§ 4.5. Generalizability: Person Detection in Artwork · p. 7YOLO models the size and shape of objects, as well as relationships between objects and where objects commonly appear.
“Like DPM, YOLO models the size and shape of objects, as well as relationships between objects and where objects commonly appear.”
Quote in the paperSubstantial claimMay combine two claims.
Premisecitation§ 3. Comparison to Other Detection Systems · p. 5MultiBox cannot perform general object detection and is still just a piece in a larger detection pipeline.
“However, MultiBox cannot perform general object detection and is still just a piece in a larger detection pipeline, requiring further image patch classification.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [8] [8] D. Erhan, C. Szegedy, A. Toshev, and D. Anguelov. Scalable object detection using deep neural networks. In Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on , pages 2155-2162. IEEE, 2014. 5, 6 - source
May combine two claims.
Interpretationnone given§ 3. Comparison to Other Detection Systems · p. 5YOLO is a general purpose detector that learns to detect a variety of objects simultaneously.
“YOLO is a general purpose detector that learns to detect a variety of objects simultaneously.”
Quote in the paperSubstantial claimMay combine two claims.
Premisereasoning§ 3. Comparison to Other Detection Systems · p. 5OverFeat cannot reason about global context and thus requires significant post-processing to produce coherent detections.
“OverFeat cannot reason about global context and thus requires significant post-processing to produce coherent detections.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [32] [32] P. Sermanet, D. Eigen, X. Zhang, M. Mathieu, R. Fergus, and Y. LeCun. Overfeat: Integrated recognition, localization and detection using convolutional networks. CoRR , abs/1312.6229, 2013. 4, 5 -
Probably not a substantial claim: may not pass S4 (based).
Interpretationnone given§ 3. Comparison to Other Detection Systems · p. 5YOLO predicts both bounding boxes and class probabilities for multiple objects of multiple classes in an image.
“YOLO predicts both bounding boxes and class probabilities for multiple objects of multiple classes in an image.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 2.1. Network Design · p. 2YOLO's network architecture is inspired by the GoogLeNet model for image classification.
“Our network architecture is inspired by the GoogLeNet model for image classification [34].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [34] [34] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. CoRR , abs/1409.4842, 2014. 2 - source
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3. Comparison to Other Detection Systems · p. 5MultiGrasp only needs to predict a single graspable region for an image containing one object.
“MultiGrasp only needs to predict a single graspable region for an image containing one object.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [27] [27] J. Redmon and A. Angelova. Real-time grasp detection using convolutional neural networks. CoRR , abs/1412.3128, 2014. 5 - source
May combine two claims.
Interpretationnone given§ 2.4. Limitations of YOLO · p. 4YOLO imposes strong spatial constraints on bounding box predictions because each grid cell only predicts two boxes and can only have one class.
“YOLO imposes strong spatial constraints on bounding box predictions since each grid cell only predicts two boxes and can only have one class.”
Quote in the paperNot a substantial claimMay combine two claims.
Interpretationreasoning§ 2.2. Training · p. 3Each bounding box predictor gets better at predicting certain sizes, aspect ratios, or classes of object, improving overall recall.
“Each predictor gets better at predicting certain sizes, aspect ratios, or classes of object, improving overall recall.”
Quote in the paperSubstantial claimMay combine two claims.
Interpretationreasoning§ 2.2. Training · p. 3In every image many grid cells do not contain any object, pushing confidence scores towards zero and often overpowering the gradient from cells that do contain objects, which can lead to model instability and training divergence early on.
“Also, in every image many grid cells do not contain any object. This pushes the 'confidence' scores of those cells towards zero, often overpowering the gradient from cells that do contain objects. This can lead to model instability, causing training to diverge early on.”
Quote in the paperSubstantial claimClassified as probably not a substantial claim.
Premisecitation§ 4.2. VOC 2007 Error Analysis · p. 6Fast R-CNN is one of the highest performing detectors on PASCAL.
“We compare YOLO to Fast RCNN since Fast R-CNN is one of the highest performing detectors on PASCAL and it's detections are publicly available.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [14] [14] R. B. Girshick. Fast R-CNN. CoRR , abs/1504.08083, 2015. 2, 5, 6, 7 - source
Classified as probably not a substantial claim.
Premisenone given§ 4.2. VOC 2007 Error Analysis · p. 6Fast R-CNN's detections are publicly available.
“We compare YOLO to Fast RCNN since Fast R-CNN is one of the highest performing detectors on PASCAL and it's detections are publicly available.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [14] [14] R. B. Girshick. Fast R-CNN. CoRR , abs/1504.08083, 2015. 2, 5, 6, 7 - source
Probably not a substantial claim: may not pass S3 (load-bearing).
Study design and conductcitation§ 4.2. VOC 2007 Error Analysis · p. 6The error analysis uses the methodology and tools of Hoiem et al. [19].
“We use the methodology and tools of Hoiem et al. [19]”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [19] [19] D. Hoiem, Y. Chodpathumwan, and Q. Dai. Diagnosing error in object detectors. In Computer Vision-ECCV 2012 , pages 340-353. Springer, 2012. 6 - source
Classified as probably not a substantial claim.
Premisecitation§ 4.5. Generalizability: Person Detection in Artwork · p. 7The Picasso Dataset and People-Art Dataset are for testing person detection on artwork.
“We compare YOLO to other detection systems on the Picasso Dataset [12] and the People-Art Dataset [3], two datasets for testing person detection on artwork.”
Quote in the paperSubstantial claim0 of 2 sources checked- cites [12] [12] S. Ginosar, D. Haas, T. Brown, and J. Malik. Detecting people in cubist art. In Computer Vision-ECCV 2014 Workshops , pages 101-116. Springer, 2014. 7 - source
- cites [3] [3] H. Cai, Q. Wu, T. Corradi, and P. Hall. The crossdepiction problem: Computer vision algorithms for recognising objects in artwork and in photographs. arXiv preprint arXiv:1505.00110 , 2015. 7 - source
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 4.1. Comparison to Other Real-Time Systems · p. 6Faster R-CNN replaces selective search with a neural network to propose bounding boxes.
“The recent Faster R-CNN replaces selective search with a neural network to propose bounding boxes, similar to Szegedy et al. [8]”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [8] [8] D. Erhan, C. Szegedy, A. Toshev, and D. Anguelov. Scalable object detection using deep neural networks. In Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on , pages 2155-2162. IEEE, 2014. 5, 6 - source
The paper relies on this without support.
Academic datasets for object detection draw the training and testing data from the same distribution.
“Academic datasets for object detection draw the training and testing data from the same distribution.”
The paper relies on this without support.
Artwork and natural images are similar in terms of the size and shape of objects.
“Artwork and natural images are very different on a pixel level but they are similar in terms of the size and shape of objects”
The paper relies on this without support.
Selective Search is tuned for natural images.
“R-CNN uses Selective Search for bounding box proposals which is tuned for natural images.”
The paper relies on this without support.
The classifier step in R-CNN only sees small regions and needs good proposals.
“The classifier step in R-CNN only sees small regions and needs good proposals.”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
YOLOv1 and YOLOv2 employed MSE/L2 loss for classification.
“which was not thoroughly investigated in prevIoUs work such as YOLOv1 [20] and YOLOv2 [51] employing MSE/L2 loss (Mean Squared Error).”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [20]
Section 2.2 (Training, p. 3) says YOLO optimizes sum-squared error and that its loss penalizes classification error when an object is present. This supports the claim for YOLOv1, but this paper does not establish what loss YOLOv2 used. (LLM, conf=0.86)
Experimental — accuracy not yet measuredYOLO series models v2-v5 are some of the most advanced object detection methods based on DNN, which have good performance in terms of speed and precision.
“the YOLO series models v2-v5 [144-147] are some of the most advanced object detection methods based on DNN, which have good performance in terms of speed and precision.”
From A survey of model compression strategies for object detection (2023) · cites this paper as [144]
The Abstract (p. 1) and §4.1 (p. 5) describe the original YOLO as a neural-network detector with real-time speed and strong accuracy relative to other real-time detectors. The paper does not evaluate YOLO versions v2–v5, so it cannot substantiate the claim about those specific models. It also notes in the Introduction (p. 2) that its YOLO model lagged behind state-of-the-art detectors in accuracy. (LLM, conf=0.88)
Experimental — accuracy not yet measuredVarious deep learning-based intelligent services and applications have changed many aspects of people's lives due to DL advantages in computer vision and natural language processing.
“As a typical and more widely used new form of applications [9], various deep learning-based intelligent services and applications have changed many aspects of people's lives due to the great advantages of Deep Learning (DL) in the fields of Computer Vision (CV) and Natural Language Processing (NLP) [10].”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [9]
The Introduction (p. 1) describes potential applications of fast object detection in driving, assistive devices, and robotics, supporting the computer-vision portion of the claim. It does not address natural language processing or establish that deep-learning applications have already changed many aspects of people's lives. (LLM, conf=0.86)
Experimental — accuracy not yet measuredYOLO's CNN predicts bounding boxes and class probabilities for all objects in an image.
“A convolutional neural network predicts the bounding boxes as well as class probabilities for all the objects depicted in an image.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
YOLO reframes object detection as a regression problem rather than classification.
“Authors of YOLO [56] have reframed the problem of object detection as a regression problem instead of classification problem.”
From Object detection using YOLO: challenges, architectural successors, datasets and applications (2023) · cites this paper as [56]
YOLO is extremely fast: a fast version runs at 155fps with VOC07 mAP=52.7%, while its enhanced version runs at 45fps with VOC07 mAP=63.4%.
“YOLO is extremely fast: a fast version of YOLO runs at 155fps with VOC07 mAP=52.7%, while its enhanced version runs at 45fps with VOC07 mAP=63.4%.”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [20]
L2 loss is prevalent in early localization research.
“L2 loss is prevalent in early research [16, 20, 51]”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [20]
The most relevant impacts of active learning methods were observed from 2014, after the release of architectures such as YOLO and Faster R-CNN, which attracted interest in applying active learning in object detection.
“The most relevant impacts of AL methods were observed from 2014, after the releasing of architectures such as YOLO [23], Faster R-CNN [33], among others, which attracted the interest of researchers and practitioners in applying AL in OD, as can be concluded from Figure 3.”
From Ten Years of Active Learning Techniques and Object Detection: A Systematic Review (2023) · cites this paper as [23]
The object detection approaches most explored seem to be those that emerged from the beginning (year 2015) such as YOLO versions, SSD, and Faster R-CNN.
“The OD approaches most explored seem to be those that emerged from the beginning (year 2015) such as YOLO versions [23-26], SSD [27], and Faster R-CNN [33].”
From Ten Years of Active Learning Techniques and Object Detection: A Systematic Review (2023) · cites this paper as [23]
In the deep learning era, bootstrap was shortly discarded in object detection during 2014-2016.
“In the deep learning era, due to the increase of computing power, bootstrap was shortly discarded in object detection during 2014-2016 [16-20].”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [20]
The Introduction (p. 1) contrasts YOLO with earlier detection methods, and Training (p. 3) describes how YOLO is trained. Neither passage addresses whether bootstrapping was discarded in object detection during 2014–2016 or attributes such a change to increased computing power; searches for bootstrapping and hard-negative mining found no passage that does. (LLM, conf=0.72)
Experimental — accuracy not yet measuredFor non-proposal-based detectors like SSD and YOLOv2, with the linear function, Soft-NMS obtains only an improvement of 0.5%.
“For detectors like SSD [18] and YOLOv2 [23] which are not proposal based, with the linear function, Soft-NMS only obtains an improvement of 0.5%.”
From Soft-NMS — Improving Object Detection with One Line of Code (2017) · cites this paper as [23]
The Abstract (p. 1) introduces the original YOLO detector, not YOLOv2. The Comparison to Other Detection Systems (p. 4) discusses non-maximal suppression, but the copy does not report a Soft-NMS test or a 0.5% improvement for YOLOv2 (searched: Soft-NMS, YOLOv2, 0.5%). (LLM, conf=0.77)
Experimental — accuracy not yet measured
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812 · see citing works
Self-citationFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 56,035 · see citing works
Self-citationGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · see citing works
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1× · see citing works
“We pretrain our convolutional layers on the ImageNet 1000-class competition dataset [29].”
MethodHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 2× · see citing works
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684 · cited 2× · see citing works
“Then, classifiers [35, 21, 13, 10] or localizers [1, 31] are used to identify objects in the feature space.”
MethodSelf-citationFast R-CNNPreprint
Girshick, R. B. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.08083 · Cited by 29,416 · see citing works
Self-citationGirshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105 · see citing works
Self-citationDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1× · see citing works
“Convolutional neural networks (CNNs) achieve impressive performance on classification tasks at real-time speeds [13].”
Object recognition from local scale-invariant features
Lowe, D. G. (1999) · Proceedings of the Seventh IEEE International Conference on Computer Vision · doi:10.1109/iccv.1999.790410 · Cited by 16,472 · cited 1× · see citing works
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodRobust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097 · cited 1× · see citing works
“Detectors for single classes like faces or people can be highly optimized since they have to deal with much less variation [36].”
BackgroundSpatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2389824 · Cited by 11,971 · see citing works
Object Detection with Discriminatively Trained Part-Based Models
Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.167 · Cited by 9,853 · cited 3× · see citing works
“Then, classifiers [35, 21, 13, 10] or localizers [1, 31] are used to identify objects in the feature space.”
MethodSelf-citationThe Pascal Visual Object Classes Challenge: A Retrospective
Everingham, M., Eslami, S. M. A., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-014-0733-5 · Cited by 7,139 · cited 1× · see citing works
“We implement this model as a convolutional neural network and evaluate it on the PASCAL VOC detection dataset [9].”
MethodImproving neural networks by preventing co-adaptation of feature detectors
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012) · arXiv · doi:10.48550/arxiv.1207.0580 · Cited by 6,382 · cited 1× · see citing works
“5 after the first connected layer prevents co-adaptation between layers [18].”
BackgroundSelective Search for Object Recognition
Uijlings, J. R. R., van de Sande, K. E. A., Gevers, T., & Smeulders, A. W. M. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0620-5 · Cited by 5,980 · cited 2× · see citing works
“Search [34] generates potential bounding boxes, a convolutional network extracts features, an SVM scores the boxes, a linear model adjusts the bounding boxes, and non-max suppression eliminates duplicate detections.”
BackgroundDeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019 · cited 1× · see citing works
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodSpatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10578-9_23 · Cited by 3,034 · cited 1× · see citing works
“[5] [37] [30] [14] [17] [27] However, only Sadeghi et al.”
An extended set of Haar-like features for rapid object detection
Lienhart, R., & Maydt, J. (2003) · Proceedings. International Conference on Image Processing · doi:10.1109/icip.2002.1038171 · Cited by 2,977 · cited 1× · see citing works
“Then, classifiers [35, 21, 13, 10] or localizers [1, 31] are used to identify objects in the feature space.”
MethodOverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6229 · Cited by 2,680 · cited 2× · see citing works
“Then, classifiers [35, 21, 13, 10] or localizers [1, 31] are used to identify objects in the feature space.”
MethodEdge Boxes: Locating Object Proposals from Edges
Zitnick, C. L., & Dollár, P. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_26 · Cited by 2,656 · cited 1× · see citing works
“These classifiers or localizers are run either in sliding window fashion over the whole image or on some subset of regions in the image [34, 15, 38].”
BackgroundRobust real-time object detection.
Viola, P. A. (2001) · Cited by 2,340 · see citing works
Going Deeper with Convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2014) · arXiv · doi:10.48550/arxiv.1409.4842 · Cited by 1,461 · cited 1× · see citing works
“Our network architecture is inspired by the GoogLeNet model for image classification [33].”
MethodA general framework for object detection
Papageorgiou, C., Oren, M., & Poggio, T. (2002) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.1998.710772 · Cited by 1,437 · cited 1× · see citing works
“Detection pipelines generally start by extracting a set of robust features from input images (Haar [25], SIFT [23], HOG [4], convolutional features [6]).”
MethodSimultaneous Detection and Segmentation
Hariharan, B., Arbeláez, P., Girshick, R., & Malik, J. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10584-0_20 · Cited by 1,176 · cited 1× · see citing works
“1 SDS [16] 50.”
Self-citationScalable Object Detection Using Deep Neural Networks
Erhan, D., Szegedy, C., Toshev, A., & Anguelov, D. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.276 · Cited by 1,161 · cited 2× · see citing works
“[8] In our tests, their most accurate model achieves 7 fps while a smaller, less accurate one runs at 18 fps.”
MethodPoselets: Body part detectors trained using 3D human pose annotations
Bourdev, L., & Malik, J. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459303 · Cited by 961 · cited 1× · see citing works
“458 32 Poselets [2] 36.”
Real-time grasp detection using convolutional neural networks
Redmon, J., & Angelova, A. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139361 · Cited by 911 · see citing works
Self-citationRobust real-time face detection
Viola, P., & Jones, M. (2005) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937709 · Cited by 898 · see citing works
Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model
Gidaris, S., & Komodakis, N. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.135 · Cited by 801 · cited 1× · see citing works
“VOC 2012 test mAP aero bike bird boat bottle bus car cat chair cow table dog horse mbike personplant sheep sofa train tv MR CNN MORE DATA [11] 73.”
MethodImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2014) · arXiv · doi:10.48550/arxiv.1409.0575 · Cited by 567 · see citing works
Diagnosing Error in Object Detectors
Hoiem, D., Chodpathumwan, Y., & Dai, Q. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33712-3_25 · Cited by 520 · cited 1× · see citing works
“[19] For each category at test time we look at the top N predictions for that category.”
BackgroundObject Detection Networks on Convolutional Feature Maps
Ren, S., He, K., Girshick, R., Zhang, X., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1504.06066 · Cited by 454 · cited 1× · see citing works
“show that adding both convolutional and connected layers to pretrained networks can improve performance [28].”
BackgroundSelf-citationObject Detection Networks on Convolutional Feature Maps
Ren, S., He, K., Girshick, R., Zhang, X., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2601099 · Cited by 454 · see citing works
Self-citationLearning to Localize Objects with Structured Output Regression
Blaschko, M. B., & Lampert, C. H. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88682-2_2 · Cited by 324 · cited 1× · see citing works
“Then, classifiers [35, 21, 13, 10] or localizers [1, 31] are used to identify objects in the feature space.”
MethodFast, Accurate Detection of 100,000 Object Classes on a Single Machine
Dean, T., Ruzon, M. A., Segal, M., Shlens, J., Vijayanarasimhan, S., & Yagnik, J. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.237 · Cited by 307 · cited 2× · see citing works
“[5] [37] [30] [14] [17] [27] However, only Sadeghi et al.”
BackgroundThe Fastest Deformable Part Model for Object Detection
Yan, J., Lei, Z., Wen, L., & Li, S. Z. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.320 · Cited by 287 · cited 4× · see citing works
“[5] [37] [30] [14] [17] [27] However, only Sadeghi et al.”
BackgroundInfluentialLin, M., Chen, Q., & Yan, S. (2013) · arXiv · doi:10.48550/arxiv.1312.4400 · Cited by 252 · see citing works
Region-Based Segmentation and Object Detection
Professor of Computer Science and Engineering, C. H. P. D. F. J., Raju, K. B., & Saikiran, B. (2019) · International Journal of Innovative Technology and Exploring Engineering · doi:10.35940/ijitee.k1353.0981119 · Cited by 170 · cited 1× · see citing works
“These classifiers or localizers are run either in sliding window fashion over the whole image or on some subset of regions in the image [34, 15, 38].”
BackgroundRegion-based Segmentation and Object Detection
Gould, S., Gao, T., & Koller, D. (2009) · Cited by 112 · see citing works
30Hz Object Detection with DPM V5
Sadeghi, M. A., & Forsyth, D. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_5 · Cited by 107 · cited 5× · see citing works
“Real-Time Detectors Train mAP FPS 100Hz DPM [30] 2007 16.”
BackgroundMethodInfluentialLenc, K., & Vedaldi, A. (2015) · Procedings of the British Machine Vision Conference 2015 · doi:10.5244/c.29.5 · Cited by 73 · see citing works
Towards Unified Object Detection and Semantic Segmentation
Dong, J., Chen, Q., Yan, S., & Yuille, A. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_20 · Cited by 70 · cited 2× · see citing works
“2 NUS NIN C2000 [7] 63.”
Detecting People in Cubist Art
Ginosar, S., Haas, D., Brown, T., & Malik, J. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16178-5_7 · Cited by 43 · see citing works
Cai, H., Wu, Q., Corradi, T., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1505.00110 · Cited by 31 · cited 2× · see citing works
“We compare YOLO to other detection systems on the Picasso Dataset [12] and the People-Art Dataset [3], two datasets for testing person detection on artwork.”
BackgroundMethod(2015) · arXiv (Cornell University) · Cited by 14 · see citing works
Detecting people in Cubist art
Ginosar, S., Haas, D., Brown, T., & Malik, J. (2015) · AI Matters · doi:10.1145/2735392.2735398 · Cited by 12 · cited 1× · see citing works
“We compare YOLO to other detection systems on the Picasso Dataset [12] and the People-Art Dataset [3], two datasets for testing person detection on artwork.”
MethodR-CNN minus RPreprint
Lenc, K., & Vedaldi, A. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.06981 · Cited by 9 · see citing works
Real-Time Grasp Detection Using Convolutional Neural NetworksPreprint
Redmon, J., & Angelova, A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.3128 · Cited by 8 · cited 2× · see citing works
“Our work is similar in design to work on grasp detection by Redmon et al [26].”
ResultSelf-citationDo More Dropouts in Pool5 Feature Maps for Better Object Detection
Shen, Z., & Xue, X. (2014) · arXiv · doi:10.48550/arxiv.1409.6911 · Cited by 7 · see citing works
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
He, K., Zhang, X., Ren, S., et al. (2014) · arXiv · doi:10.48550/arxiv.1406.4729
Object detection via a multi-region & semantic segmentation-aware CNN model
Gidaris, S., & Komodakis, N. (2015) · arXiv · doi:10.48550/arxiv.1505.01749
Flagged first, then by citations
Research works printed but not linked: 1
- mishkin, 0, Models accuracy on imagenet 2012 val
Cited by
Sorted by citations
(2016) · Cited by 31,590 · see citing works
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.324 · Cited by 30,581 · see citing works
Self-citationSSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128 · see citing works
YOLO9000: Better, Faster, Stronger
Redmon, J., & Farhadi, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.690 · Cited by 19,892 · see citing works
Self-citationEnd-to-End Object Detection with Transformers
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58452-8_13 · Cited by 18,285 · see citing works
YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00721 · Cited by 13,198 · see citing works
“However, in recent years, if we take object detection as an example, researchers often use the quality and distribution of prediction output by the network, and then consider together with the ground truth to use some calculation and optimization methods to generate a reliable soft label [61, 8, 36, 99, 91, 44, 43, 90…”
MethodYOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022) · arXiv · doi:10.48550/arxiv.2207.02696 · Cited by 13,205 · see citing works
“However, in recent years, if we take object detection as an example, researchers often use the quality and distribution of prediction output by the network, and then consider together with the ground truth to use some calculation and optimization methods to generate a reliable soft label [61, 8, 36, 99, 91, 44, 43, 90…”
MethodYOLOv4: Optimal Speed and Accuracy of Object Detection
Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020) · arXiv · doi:10.48550/arxiv.2004.10934 · Cited by 10,307 · see citing works
A Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000 · see citing works
Focal Loss for Dense Object Detection
Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2858826 · Cited by 9,556 · see citing works
Self-citationDeformable Convolutional Networks
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.89 · Cited by 7,513 · see citing works
Cascade R-CNN: Delving Into High Quality Object Detection
Cai, Z., & Vasconcelos, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00644 · Cited by 7,370 · see citing works
FCOS: Fully Convolutional One-Stage Object Detection
Tian, Z., Shen, C., Chen, H., & He, T. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00972 · Cited by 7,013 · see citing works
Recent advances in convolutional neural networks
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J., et al. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.10.013 · Cited by 6,576 · see citing works
Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression
Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., & Savarese, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00075 · Cited by 6,612 · see citing works
Object Detection With Deep Learning: A Review
Zhao, Z.-Q., Zheng, P., Xu, S.-T., & Wu, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2876865 · Cited by 5,545 · see citing works
A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
Li, Z., Liu, F., Yang, W., Peng, S., & Zhou, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3084827 · Cited by 5,273 · see citing works
“Afterward, YOLO v2 [130] proposed a new classification model, darknet-19, which includes 19 convolutional layers and five max-pooling layers.”
MethodInfluentialBottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S. J., & Zhang, L. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00636 · Cited by 5,117 · see citing works
DETRs Beat YOLOs on Real-time Object Detection
Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., & Chen, J. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01605 · Cited by 5,020 · see citing works
“YOLOv1 [29] is the first CNN-based one-stage object detector to achieve true real-time object detection.”
BackgroundDistance-IoU Loss: Faster and Better Learning for Bounding Box Regression
Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., & Ren, D. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6999 · Cited by 5,288 · see citing works
YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
Wang, C.-Y., Yeh, I.-H., & Mark Liao, H.-Y. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-72751-1_1 · Cited by 4,823 · see citing works
Object Detection in 20 Years: A Survey
Zou, Z., Chen, K., Shi, Z., Guo, Y., & Ye, J. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3238524 · Cited by 3,689 · see citing works
“L2 loss is prevalent in early research [16], [20], [51], but it is highly affected by outliers and prone to gradient explosion.”
InfluentialCornerNet: Detecting Objects as Paired Keypoints
Law, H., & Deng, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01264-9_45 · Cited by 3,852 · see citing works
CenterNet: Keypoint Triplets for Object Detection
Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., & Tian, Q. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00667 · Cited by 4,079 · see citing works
Transformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022) · ACM Computing Surveys · doi:10.1145/3505244 · Cited by 3,595 · see citing works
SECOND: Sparsely Embedded Convolutional Detection
Yan, Y., Mao, Y., & Li, B. (2018) · Sensors · doi:10.3390/s18103337 · Cited by 3,352 · see citing works
Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources
Zhu, X. X., Tuia, D., Mou, L., Xia, G.-S., Zhang, L., Xu, F., & Fraundorfer, F. (2017) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2017.2762307 · Cited by 3,400 · see citing works
A Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. (2020) · UTS ePRESS (University of Technology Sydney) · Cited by 3,174 · see citing works
PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud
Shi, S., Wang, X., & Li, H. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00086 · Cited by 3,093 · see citing works
Survey on deep learning with class imbalance
Johnson, J. M., & Khoshgoftaar, T. M. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0192-5 · Cited by 3,032 · see citing works
YOLOX: Exceeding YOLO Series in 2021
Ge, Z., Liu, S., Wang, F., Li, Z., & Sun, J. (2021) · arXiv · doi:10.48550/arxiv.2107.08430 · Cited by 2,965 · see citing works
A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS
Terven, J. R., Esparza, D. M. C., & Romero-González, J.-A. (2023) · Machine Learning and Knowledge Extraction · doi:10.3390/make5040083 · Cited by 3,702 · see citing works
Deep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01247-4 · Cited by 2,965 · see citing works
A Review of Yolo Algorithm Developments
Jiang, P., Ergu, D., Liu, F., Cai, Y., & Ma, B. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.01.135 · Cited by 2,783 · see citing works
Albumentations: fast and flexible image augmentations
Buslaev, A., Iglovikov, V. I., Khvedchenya, E., Parinov, A., Druzhinin, M., & Kalinin, A. A. (2020) · Information · doi:10.3390/info11020125 · Cited by 2,714 · see citing works
Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors
Huang, J., Rathod, V., Sun, C., Zhu, M., Korattikara, A., Fathi, A., Fischer, I., Wojna, Z., Song, Y., Guadarrama, S., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.351 · Cited by 2,743 · see citing works
Channel Pruning for Accelerating Very Deep Neural Networks
He, Y., Zhang, X., & Sun, J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.155 · Cited by 2,647 · see citing works
Deep learning for visual understanding: A review
Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S., & Lew, M. S. (2016) · Neurocomputing · doi:10.1016/j.neucom.2015.09.116 · Cited by 2,504 · see citing works
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2918951 · Cited by 2,455 · see citing works
Zhang, S., Chi, C., Yao, Y., Lei, Z., & Li, S. Z. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00978 · Cited by 2,531 · see citing works
Object detection in optical remote sensing images: A survey and a new benchmark
Li, K., Wan, G., Cheng, G., Meng, L., & Han, J. (2020) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.11.023 · Cited by 2,317 · see citing works
Soft-NMS — Improving Object Detection with One Line of Code
Bodla, N., Singh, B., Chellappa, R., & Davis, L. S. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.593 · Cited by 2,274 · see citing works
“For detectors like SSD [18] and YOLOv2 [23] which are not proposal based, with the linear function, Soft-NMS only obtains an improvement of 0.”
BackgroundMethodInfluentialYOLACT: Real-Time Instance Segmentation
Bolya, D., Zhou, C., Xiao, F., & Lee, Y. J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00925 · Cited by 2,536 · see citing works
Zhu, X., Lyu, S., Wang, X., & Zhao, Q. (2021) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw54120.2021.00312 · Cited by 2,442 · see citing works
Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey
Jing, L., & Tian, Y. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2992393 · Cited by 2,036 · see citing works
Focal and efficient IOU loss for accurate bounding box regression
Zhang, Y., Ren, W., Zhang, Z., Jia, Z., Wang, L., & Tan, T. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.07.042 · Cited by 2,108 · see citing works
Cascade R-CNN: High Quality Object Detection and Instance Segmentation
Cai, Z., & Vasconcelos, N. M. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2956516 · Cited by 1,984 · see citing works
A Survey of Autonomous Driving: <i>Common Practices and Emerging Technologies</i>
Yurtsever, E., Lambert, J., Carballo, A., & Takeda, K. (2020) · IEEE Access · doi:10.1109/access.2020.2983149 · Cited by 1,889 · see citing works
“Once surfaces are estimated, model fitting is used to establish the continuity of the road and lanes.”
BackgroundA survey of deep learning techniques for autonomous driving
Grigorescu, S., Trasnea, B., Cocias, T., & Macesanu, G. (2020) · Journal of Field Robotics · doi:10.1002/rob.21918 · Cited by 1,809 · see citing works
YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., et al. (2022) · arXiv · doi:10.48550/arxiv.2209.02976 · Cited by 1,792 · see citing works
Receptive Field Block Net for Accurate and Fast Object Detection
Liu, S., Huang, D., & Wang, Y. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01252-6_24 · Cited by 1,885 · see citing works
Adversarial Examples: Attacks and Defenses for Deep Learning
Yuan, X., He, P., Zhu, Q., & Li, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2886017 · Cited by 1,733 · see citing works
Libra R-CNN: Towards Balanced Learning for Object Detection
Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., & Lin, D. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00091 · Cited by 1,863 · see citing works
The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
Jégou, S., Drozdzal, M., Vázquez, D., Romero, A., & Bengio, Y. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.156 · Cited by 1,762 · see citing works
AutoML: A survey of the state-of-the-art
He, X. J., Zhao, K., & Chu, X. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106622 · Cited by 1,911 · see citing works
Single-Shot Refinement Neural Network for Object Detection
Zhang, S., Wen, L., Bian, X., Lei, Z., & Li, S. Z. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00442 · Cited by 1,678 · see citing works
Scaled-YOLOv4: Scaling Cross Stage Partial Network
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.01283 · Cited by 1,756 · see citing works
TOOD: Task-aligned One-stage Object Detection
Feng, C., Zhong, Y., Gao, Y., Scott, M. R., & Huang, W. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00349 · Cited by 1,668 · see citing works
A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
Cai, Z., Fan, Q., Feris, R. S., & Vasconcelos, N. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_22 · Cited by 1,605 · see citing works
RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild
Deng, J., Guo, J., Ververas, E., Kotsia, I., & Zafeiriou, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00525 · Cited by 1,681 · see citing works
A State-of-the-Art Survey on Deep Learning Theory and Architectures
Alom, M. Z., Taha, T. M., Yakopcic, C., Westberg, S. K. E., Sidike, P., Nasrin, M. S., Hasan, M., Essen, B. C. V., Awwal, A. A. S., & Asari, V. K. (2019) · Electronics · doi:10.3390/electronics8030292 · Cited by 1,719 · see citing works
ICNet for Real-Time Semantic Segmentation on High-Resolution Images
Zhao, H., Qi, X., Shen, X., Shi, J., & Jia, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_25 · Cited by 1,709 · see citing works
Cell Detection with Star-Convex Polygons
Schmidt, U., Weigert, M., Broaddus, C., & Myers, G. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-00934-2_30 · Cited by 1,826 · see citing works
Relation Networks for Object Detection
Hu, H., Gu, J., Zhang, Z., Dai, J., & Wei, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00378 · Cited by 1,524 · see citing works
Synthetic Data for Text Localisation in Natural Images
Gupta, A., Vedaldi, A., & Zisserman, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.254 · Cited by 1,563 · see citing works
Schwartz, R., Dodge, J., Smith, N. A., & Etzioni, O. (2020) · Communications of the ACM · doi:10.1145/3381831 · Cited by 1,647 · see citing works
Object detection using YOLO: challenges, architectural successors, datasets and applications
Diwan, T., Anirudh, G., & Tembhurne, J. V. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13644-y · Cited by 1,549 · see citing works
“18 YOLO architecture for object detection and localization [56] predicts there ’ s an object.”
BackgroundHybrid Task Cascade for Instance Segmentation
Chen, K., Pang, J., Wang, J., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Shi, J., Ouyang, W., et al. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00511 · Cited by 1,587 · see citing works
SwinFusion: Cross-domain Long-range Learning for General Image Fusion via Swin Transformer
Ma, J., Tang, L., Fan, F., Huang, J., Mei, X., & Ma, Y. (2022) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2022.105686 · Cited by 1,557 · see citing works
LinkNet: Exploiting encoder representations for efficient semantic segmentation
Chaurasia, A., & Culurciello, E. (2017) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip.2017.8305148 · Cited by 1,972 · see citing works
Zheng, Z., Wang, P., Ren, D., Liu, W., Ye, R., Hu, Q., & Zuo, W. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3095305 · Cited by 1,552 · see citing works
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2970550 · Cited by 1,498 · see citing works
“types of models rather than the standard model (such as YOLO [9]): specialized models that waive the generality of standard models in exchange for faster inference, and difference detectors that identify temporal differences across input data.”
BackgroundMethodSparse R-CNN: End-to-End Object Detection with Learnable Proposals
Sun, P., Zhang, R., Jiang, Y., Kong, T., Xu, C., Zhan, W., Tomizuka, M., Li, L., Yuan, Z., Wang, C., et al. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01422 · Cited by 1,617 · see citing works
A Survey on Performance Metrics for Object-Detection Algorithms
Padilla, R., Netto, S. L., & da Silva, E. A. B. (2020) · 2020 International Conference on Systems, Signals and Image Processing (IWSSIP) · doi:10.1109/iwssip48289.2020.9145130 · Cited by 1,605 · see citing works
Deep Learning for IoT Big Data and Streaming Analytics: A Survey
Mohammadi, M., Al-Fuqaha, A., Sorour, S., & Guizani, M. (2018) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2018.2844341 · Cited by 1,471 · see citing works
The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
Neuhold, G., Ollmann, T., Bulo, S. R., & Kontschieder, P. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.534 · Cited by 1,434 · see citing works
Feng, D., Haase-Schutz, C., Rosenbaum, L., Hertlein, H., Glaser, C., Timm, F., Wiesbeck, W., & Dietmayer, K. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.2972974 · Cited by 1,425 · see citing works
Pouyanfar, S., Sadiq, S. B., Yan, Y., Tian, H., Tao, Y., Reyes, M. P., Shyu, M., Chen, S., & Iyengar, S. S. (2018) · ACM Computing Surveys · doi:10.1145/3234150 · Cited by 1,508 · see citing works
Oriented R-CNN for Object Detection
Xie, X., Cheng, G., Wang, J., Yao, X., & Han, J. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00350 · Cited by 1,457 · see citing works
An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features
He, Y., Song, K., Meng, Q., & Yan, Y. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2019.2915404 · Cited by 1,341 · see citing works
“The representative direct regression methods are YOLO [29] and SSD [30].”
MethodA Survey of Deep Learning-Based Object Detection
Jiao, L., Zhang, F., Liu, F., Yang, S., Li, L., Feng, Z., & Qu, R. (2019) · IEEE Access · doi:10.1109/access.2019.2939201 · Cited by 1,447 · see citing works
Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
Bell, S., Zitnick, C. L., Bala, K., & Girshick, R. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.314 · Cited by 1,368 · see citing works
Self-citationSPHIRE-crYOLO is a fast and accurate fully automated particle picker for cryo-EM
Wagner, T., Merino, F., Stabrin, M., Moriya, T., Antoni, C., Apelbaum, A., Hagel, P., Sitsel, O., Raisch, T., Prumbaum, D., et al. (2019) · Communications Biology · doi:10.1038/s42003-019-0437-z · Cited by 1,217 · see citing works
Arbitrary-Oriented Scene Text Detection via Rotation Proposals
Ma, J., Shao, W., Ye, H., Wang, L., Wang, H., Zheng, Y., & Xue, X. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2818020 · Cited by 1,477 · see citing works
Norouzzadeh, M. S., Nguyen, A., Kosmala, M., Swanson, A., Palmer, M. S., Packer, C., & Clune, J. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1719367115 · Cited by 1,230 · see citing works
Learning From Noisy Labels With Deep Neural Networks: A Survey
Song, H., Kim, M., Park, D., Shin, Y., & Lee, J.-G. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3152527 · Cited by 1,407 · see citing works
PIXOR: Real-time 3D Object Detection from Point Clouds
Yang, B., Luo, W., & Urtasun, R. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00798 · Cited by 1,249 · see citing works
Hussain, M. (2023) · Machines · doi:10.3390/machines11070677 · Cited by 1,217 · see citing works
3D Bounding Box Estimation Using Deep Learning and Geometry
Mousavian, A., Anguelov, D., Flynn, J., & Kosecka, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.597 · Cited by 1,129 · see citing works
DenseCap: Fully Convolutional Localization Networks for Dense Captioning
Johnson, J., Karpathy, A., & Fei-Fei, L. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.494 · Cited by 1,161 · see citing works
RepPoints: Point Set Representation for Object Detection
Yang, Z., Liu, S., Hu, H., Wang, L., & Lin, S. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00975 · Cited by 1,307 · see citing works
Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring
Spencer, B. F., Hoskere, V., & Narazaki, Y. (2019) · Engineering · doi:10.1016/j.eng.2018.11.030 · Cited by 1,272 · see citing works
D2-Net: A Trainable CNN for Joint Description and Detection of Local Features
Dusmanu, M., Rocco, I., Pajdla, T., Pollefeys, M., Šivic, J., Torii, A., & Sattler, T. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00828 · Cited by 1,190 · see citing works
Mehta, D., Sridhar, S., Sotnychenko, O., Rhodin, H., Shafiei, M., Seidel, H., Xu, W., Casas, D., & Theobalt, C. (2017) · ACM Transactions on Graphics · doi:10.1145/3072959.3073596 · Cited by 1,156 · see citing works
A Light CNN for Deep Face Representation With Noisy Labels
Wu, X., He, R., Sun, Z., & Tan, T. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2833032 · Cited by 1,213 · see citing works
R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
Yang, X., Yan, J., Feng, Z., & He, T. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i4.16426 · Cited by 1,315 · see citing works
A review of convolutional neural networks in computer vision
Zhao, X., Wang, L., Zhang, Y., Han, X., Deveci, M., & Parmar, M. D. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10721-6 · Cited by 1,326 · see citing works
Tang, L., Yuan, J., & Ma, J. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.12.004 · Cited by 1,161 · see citing works
CornerNet: Detecting Objects as Paired Keypoints
Law, H., & Deng, J. (2019) · International Journal of Computer Vision · doi:10.1007/s11263-019-01204-1 · Cited by 1,294 · see citing works
Convolutional neural network: a review of models, methodologies and applications to object detection
Dhillon, A., & Verma, G. K. (2020) · Progress in Artificial Intelligence · doi:10.1007/s13748-019-00203-0 · Cited by 1,119 · see citing works
- Authors
- Redmon, J., Divvala, S., Girshick, R., & Farhadi, A.
- Affiliations
- University of Washington (US)
- Meta (United States) (US)
- Venue
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2016-06
- Pages
- 779-788
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W1483870316
- Cited by
- 53,803
- References
- 42
- Citations by year
- 2026: 5347 · 2025: 8912 · 2024: 8953 · 2023: 8264 · 2022: 6785 · 2021: 5741 · 2020: 4223 · 2019: 3286 · 2018: 1560 · 2017: 635 · 2016: 90 · 2015: 4 · 2014: 1
- FWCI
- 644.23
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Zenodo (CERN European Organization for Nuclear Research) (cc-by)
- Funders
- National Science Foundation (1338054)
- Office of Naval Research (N00014-13-1-0720, N00014)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- object detection, YOLO, real-time detection, bounding box regression, end-to-end learning, false positive reduction, domain generalization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-10.
Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-10.
Cited sources are checked by gpt-6-sol.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review