You Only Look Once: Unified, Real-Time Object Detection
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index; 8 of the 25 sources its claims cite were checked for support.
Abstract
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.
Overview
CoChat Summary
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
Figures





Verification
Claims the paper makes
6 Valid · 8 Not valid · 15 Not checked · 92 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“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.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
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)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“To avoid overfitting we use dropout and extensive data augmentation.”
What the sources say
- Partly supportedcites [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 - sourceExperimental — accuracy not yet measured
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)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“However, only 30Hz DPM [31] actually runs in real-time.”
What the sources say
- Supportedcites [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
The Introduction (p.1) states that 'except for certain objects including face, pedestrians and certain rigid objects, detectors do not currently run at video rate' and that the presented architecture detects the 20 PASCAL VOC categories simultaneously at 30Hz, i.e. at video/real-time rate. The Abstract (p.1) and Table 2 (Method) bound the comparison to other DPM speed-up efforts: reference DPM at 0.07Hz, the fastest GPU 'Vanilla DPM' at ~1Hz, FTVQ at 0.53s, and 'over an order of magnitude faster than the previous fastest DPM implementation', so none of the listed variants reaches real-time. Thus our copy supports both parts of the attribution: that this 30Hz DPM runs in real-time and that it is the only such DPM among the speed-up efforts compared. (LLM, conf=0.82)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“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.”
What the sources say
- Could not verifycites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
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)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“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.”
What the sources say
- Partly supportedcites [20] [20] K. Lenc and A. Vedaldi. R-cnn minus r. arXiv preprint arXiv:1506.06981 , 2015. 5, 6 - sourceExperimental — accuracy not yet measured
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)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
84 more claims
Create a free account to see all 121 claims and to verify the 2 references still open.
- Probably not a substantial claim. 17
- It may state two separate claims as one. 15
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“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]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“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]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“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]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“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]
The cited source says what the claim attributes to it.
In the citing paper
“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]
6 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Faster 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 73,472
Self-citationFaster 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
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
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×
“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×
“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×
“Then, classifiers [35, 21, 13, 10] or localizers [1, 31] are used to identify objects in the feature space.”
MethodSelf-citationGirshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
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×
“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×
“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×
“Detectors for single classes like faces or people can be highly optimized since they have to deal with much less variation [36].”
Background
Cited by
Items 17,001–17,100 of 51,399
Kellenberger, B., Marcos, D., & Tuia, D. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-10997-4_40 · Cited by 10
Chen, J.-B., Wang, Z.-H., & Li, H. (2018) · Journal of Systems Engineering and Electronics · doi:10.21629/jsee.2018.06.17 · Cited by 8
VisKit: Web-Based Interactive IoT Management with Deep Visual Object Detection
Hwang, C.-E., Lee, S.-H., & Jeong, J.-W. (2019) · Journal of Sensor and Actuator Networks · doi:10.3390/jsan8010012 · Cited by 10
Herzog, M., & Dietmayer, K. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917011 · Cited by 14
A Deep Learning Framework for Automatic Airplane Detection in Remote Sensing Satellite Images
Hassan, A., Hussein, W. M., Said, E., & Hanafy, M. E. (2019) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero.2019.8741938 · Cited by 10
Neural Network-Based Vehicle and Pedestrian Detection for Video Analysis System
Babayan, P. V., Ershov, M. D., & Erokhin, D. Y. (2019) · Mediterranean Conference on Embedded Computing (MECO) · doi:10.1109/meco.2019.8760125 · Cited by 10
Orientation Robust Object Detection in Aerial Images Based on R-NMS
Liu, Q. Q., & Li, J. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2019.06.102 · Cited by 10
See-your-room: indoor localization with camera vision
Sun, M., Zhang, L., Liu, Y., Miao, X., & Ding, X. X. (2019) · ACM Turing Celebration Conference - China (ACM TURC) · doi:10.1145/3321408.3321581 · Cited by 20
A Product Engine for Energy-Efficient Execution of Binary Neural Networks Using Resistive Memories
Vieira, J., Giacomin, E., Qureshi, Y. M., et al. (2019) · IFIP/IEEE International Conference on Very Large Scale Integration · doi:10.1109/vlsi-soc.2019.8920343 · Cited by 10
Fast QR code detection based on BING and AdaBoost-SVM
Yuan, B., Li, Y., Jiang, F., et al. (2019) · IEEE International Conference on High Performance Switching and Routing (HPSR) · doi:10.1109/hpsr.2019.8808000 · Cited by 10
Image Detector Based Automatic 3D Data Labeling and Training for Vehicle Detection on Point Cloud
Chen, Z., Liao, Q., Wang, Z., Liu, Y., & Liu, M. (2019) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2019.8813818 · Cited by 10
Pezzica, C., Schroeter, J., Prizeman, O., Jones, C. B., & Rosin, P. L. (2019) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-iv-2-w6-123-2019 · Cited by 16
Multi-scale Feature Fusion Single Shot Object Detector Based on DenseNet
Zhai, M., Liu, J., Zhang, W., Liu, C., Li, W., & Cao, Y. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-27541-9_37 · Cited by 12
SEMANTIC SEGMENTATION OF MANMADE LANDSCAPE STRUCTURES IN DIGITAL TERRAIN MODELS
Kazimi, B., Thiemann, F., & Sester, M. (2019) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-iv-2-w7-87-2019 · Cited by 13
Design and Implementation of Image Electronic Fence with 5G technology for Smart Farms
Hsu, C.-K., Chiu, Y.-H., Wu, K.-R., et al. (2019) · IEEE VTS Asia Pacific Wireless Communications Symposium (APWCS) · doi:10.1109/vts-apwcs.2019.8851659 · Cited by 10
SDV-Net: A Two-Stage Convolutional Neural Network for Smoky Diesel Vehicle Detection
Wang, X., Kang, Y., & Cao, Y. H. (2019) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2019.8865919 · Cited by 10
Geosocial Media as a Proxy for Security: A Review
Han, Z., Li, S., Cui, C., Han, D., & Song, H. (2019) · IEEE Access · doi:10.1109/access.2019.2949115 · Cited by 11
Accurate and Real-Time Object Detection Based on Bird's Eye View on 3D Point Clouds
Zhang, Y., Xiang, Z., Qiao, C., & Chen, S. (2019) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00032 · Cited by 15
Instance search based on weakly supervised feature learning
Lin, J., Yu, Z., & Zhao, W. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.11.029 · Cited by 9
Prediction of Driver’s Attention Points Based on Attention Model
Zhao, S., Han, G., Zhao, Q., & Wei, P. (2020) · Applied Sciences · doi:10.3390/app10031083 · Cited by 10
An End-to-End Abnormal Fastener Detection Method Based on Data Synthesis
Dong, B., Li, Q., Wang, J., Huang, W., Dai, P., & Wang, S. (2019) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai.2019.00029 · Cited by 11
Object detection in optical remote sensing images by integrating object-to-object relationships
Tian, Z., Zhan, R., Wang, W., He, Z., Zhang, J., & Zhuang, Z. (2020) · Remote Sensing Letters · doi:10.1080/2150704x.2020.1722330 · Cited by 11
Masrour, T., Hassani, I. E., & Bouchama, M. S. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-36671-1_18 · Cited by 16
Interest-Oriented Video Summarization with Keyframe Extraction
Gunawardena, P., Sudarshana, H., Amila, O., Nawaratne, R., Alahakoon, D., Perera, A. S., & Chitraranjan, C. D. (2019) · International Conference on Advances in ICT for Emerging Regions · doi:10.1109/icter48817.2019.9023769 · Cited by 11
Xun, L., Tran-Thanh, L., Al‐Hashimi, B. M., & Merrett, G. V. (2019) · ACM/IEEE Workshop on Machine Learning for CAD (MLCAD) · doi:10.1109/mlcad48534.2019.9142052 · Cited by 11
An Improved Vehicle Detection Algorithm Based on YOLOV3
Sun, X., Huang, Q., Li, Y., & Huang, Y. (2019) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-sustaincom-socialcom48970.2019.00208 · Cited by 11
An End-to-End Approach for Recognition of Modern and Historical Handwritten Numeral Strings
Hochuli, A. G., Britto, A. S., Barddal, J. P., Sabourin, R., & Oliveira, L. S. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207468 · Cited by 10
Standing on Giant’s Shoulders: Newcomer’s Experience from the Amazon Robotics Challenge 2017
Ricardez, G. A. G., Hafi, L. E., & von Drigalski, F. (2020) · Springer eBooks · doi:10.1007/978-3-030-35679-8_8 · Cited by 15
Detector-SegMentor Network for Skin Lesion Localization and Segmentation
Saini, S., Gupta, D., & Tiwari, A. K. (2020) · Communications in computer and information science · doi:10.1007/978-981-15-8697-2_55 · Cited by 13
Cho, Y., Lee, S. M., Cho, Y., Lee, J., Park, B., Lee, G., Kim, N., & Seo, J. B. (2020) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22508 · Cited by 10
Knowledge-Based Object Localization in Scanning Electron Microscopy Images for Hardware Assurance
Lu, H., Wilson, R. S., Vashistha, N., et al. (2020) · Proceedings - International Symposium for Testing and Failure Analysis · doi:10.31399/asm.cp.istfa2020p0020 · Cited by 10
Xiang, Z., Seeling, P., & Fitzek, F. H. P. (2021) · Applied Sciences · doi:10.3390/app11052177 · Cited by 10
Optimization of Underwater Marker Detection Based on YOLOv3
Jiang, N., Wang, J., Kong, L., Zhang, S., & Dong, J. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.04.106 · Cited by 13
The Series Elastic Gripper Design, Object Detection, and Recognition by Touch
Kaya, O., Tağlıoğlu, G. B., & Ertuğrul, Ş. (2021) · Journal of Mechanisms and Robotics · doi:10.1115/1.4051520 · Cited by 10
Research on workpiece location algorithm based on improved SSD
Li, L., Fu, M., Zhang, T., & Wu, H. (2021) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir-01-2021-0005 · Cited by 12
Rahaman, M. A., Ali, M. M., Ahmed, K., Bui, F. M., & Mahmud, S. M. H. (2022) · International Conference on Computing Advancements (ICCA) · doi:10.1145/3542954.3543000 · Cited by 12
A Real-Time License Plate Detection Method Using a Deep Learning Approach
Khazaee, S., Tourani, A., Soroori, S., Shahbahrami, A., & Suen, C. Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59830-3_37 · Cited by 15
SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree ImagesPreprint
Lee, Y., Jeong, J., Yun, J., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.08196 · Cited by 10
Penobscot Dataset: Fostering Machine Learning Development for Seismic InterpretationPreprint
Baroni, L. R., Silva, R. M., Ferreira, R. S., Civitarese, D., Szwarcman, D., & Brazil, E. V. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.12060 · Cited by 15
Single Pixel Reconstruction for One-stage Instance SegmentationPreprint
Yu, J., Yao, J., Zhang, J., Zhou, Y., & Tao, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.07426 · Cited by 8
Single-Camera Basketball Tracker through Pose and Semantic Feature FusionPreprint
Arbués-Sangüesa, A., Ballester, C., & Haro, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.02042 · Cited by 28
Efficient Deep Neural NetworksPreprint
Wu, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.08926 · Cited by 15
AFP-Net: Realtime Anchor-Free Polyp Detection in ColonoscopyPreprint
Wang, D., Zhang, N., Sun, X., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.02477 · Cited by 10
Double Anchor R-CNN for Human Detection in a CrowdPreprint
Zhang, K., Xiong, F., Sun, P., Hu, L., Li, B., & Yu, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.09998 · Cited by 60
Samarth, C. A. G., Bhowmik, N., & Breckon, T. P. (2019) · arXiv (Cornell University) · Cited by 10
Traffic Signs Detection and Recognition System using Deep LearningPreprint
Zaki, P. S., William, M. M., Soliman, B. K., Alexsan, K. G., Khalil, K. K., & El-Moursy, M. A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.03256 · Cited by 36
Scan2Plan: Efficient Floorplan Generation from 3D Scans of Indoor ScenesPreprint
Phalak, A., Badrinarayanan, V., & Rabinovich, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.07356 · Cited by 21
FGN: Fully Guided Network for Few-Shot Instance SegmentationPreprint
Fan, Z., Yu, J.-G., Liang, Z., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.13954 · Cited by 10
Object-oriented SLAM using Quadrics and Symmetry Properties for Indoor EnvironmentsPreprint
Liao, Z., Wang, W., Qi, X., Zhang, X., Xue, L., Jiao, J., & Wei, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.05303 · Cited by 17
ApproxNet: Content and Contention-Aware Video Analytics System for Embedded ClientsPreprint
Xu, R., Kumar, R., Wang, P., Bai, P., Meghanath, G., Chaterji, S., Mitra, S., & Bagchi, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.02068 · Cited by 11
FenceMask: A Data Augmentation Approach for Pre-extracted Image FeaturesPreprint
Li, P., Li, X., & Long, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.07877 · Cited by 41
High-Throughput Image-Based Plant Stand Count Estimation Using Convolutional Neural NetworksPreprint
Khaki, S., Pham, H., Han, Y., Kent, W., & Wang, L. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.11.05.370437 · Cited by 10
Ankile, L., Heggland, M. F., & Krange, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.12960 · Cited by 32
3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object DetectionPreprint
Wang, H., Cong, Y., Litany, O., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.04355 · Cited by 10
MRI Images, Brain Lesions and Deep LearningPreprint
Castillo, D., Lakshminarayanan, V., & Rodríguez-Álvarez, M. J. (2021) · Preprints.org · doi:10.20944/preprints202101.0426.v1 · Cited by 10
TOP: Backdoor Detection in Neural Networks via Transferability of PerturbationPreprint
Huster, T. P., & Ekwedike, E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.10274 · Cited by 18
Scene Graphs: A Survey of Generations and Applications.Preprint
Chang, X., Ren, P., Xu, P., Li, Z., Chen, X., & Hauptmann, A. G. (2021) · arXiv (Cornell University) · Cited by 11
Oriented RepPoints for Aerial Object DetectionPreprint
Li, W., Chen, Y., Hu, K., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.11111 · Cited by 10
TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive FieldsPreprint
Xu, T.-X., Guo, Y.-C., Lai, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.11605 · Cited by 10
Certification of embedded systems based on Machine Learning: A surveyPreprint
Vidot, G., Gabreau, C., Ober, I., & Ober, I. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.07221 · Cited by 19
MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger TokensPreprint
Fang, J., Xie, L., Wang, X., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.15168 · Cited by 10
LaplaceNet: A Hybrid Energy-Neural Model for Deep Semi-Supervised ClassificationPreprint
Sellars, P., Avilés-Rivero, A. I., & Schönlieb, C. (2021) · arXiv (Cornell University) · Cited by 10
Adding Binary Search Connections to Improve DenseNet PerformancePreprint
Kumar, R. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3545071 · Cited by 11
A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and DatasetsPreprint
Muzammul, M., & Li, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.07927 · Cited by 28
Improved YOLOX-X based UAV aerial photography object detection algorithmPreprint
Wang, X., He, N., Hong, C., et al. (2022) · Research Square · doi:10.21203/rs.3.rs-2140458/v1 · Cited by 10
Accurate detection and identification of insects from camera trap images with deep learningPreprint
Bjerge, K., Alison, J., Dyrmann, M., et al. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.10.25.513484 · Cited by 10
Augustine, B. C., Koneff, M. D., Pickens, B. A., & Royle, J. A. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.02.20.529272 · Cited by 9
Vehicle Detection and Tracking from Surveillance Cameras in Urban Scenes
Messoussi, O., de Magalhães, F. G., Lamarre, F., Perreault, F., Sogoba, I., Bilodeau, G.-A., & Nicolescu, G. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-90436-4_15 · Cited by 9
Towards Recognizing Unseen Categories in Unseen Domains
Mancini, M., Akata, Z., Ricci, E., & Caputo, B. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58592-1_28 · Cited by 9
Gaus, Y. F. A., Bhowmik, N., Akçay, S., Guillen-Garcia, P. M., Barker, J. W., & Breckon, T. P. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8851829 · Cited by 87
Detecting social distancing by using Detectron2 and OpenCV
Mahammad, F. S., Phani, K. V. S., Ramadevi, N., et al. (2024) · AIP conference proceedings · doi:10.1063/5.0212686 · Cited by 9
End‐to‐End Cascaded Image Restoration and Object Detection for Rain and Fog Conditions
Li, P., Ni, J. F., & Tao, D. (2025) · IET Computer Vision · doi:10.1049/cvi2.70021 · Cited by 10
Efficient real-time palm oil tree detection and counting using YOLOv8 deployed on edge devices
Farhan, M., Akhtar, M. N., & Bakar, E. A. (2025) · Journal of Umm Al-Qura University for Engineering and Architecture · doi:10.1007/s43995-025-00164-7 · Cited by 16
“YOLO is a popular object detection method which utilizes Convolutional Neural Networks (CNNs) as the back-bone [29].”
Yu, H., Luo, Q., Peng, W., et al. (2025) · Sensors · doi:10.3390/s25165004 · Cited by 9
“While achieving 96.7% mAP@0 [8] in 2016.”
InfluentialWang, D., Shi, L., Yin, H., Cheng, Y., Liu, S., Wu, S., Yang, G., Dong, Q., Ge, J., & Li, Y. (2025) · Plants · doi:10.3390/plants14162475 · Cited by 9
“First, in dense target detection, both the single-stage mechanism of YOLO [18,19] and improved Mask R-CNN/Faster R-CNN variants demonstrate recall rates below 90% under occlusion scenarios [25,26].”
Few-Shot Adaptation of Grounding DINO for Agricultural Domain
Singh, R., Puhl, R. B., Dhakal, K., & Sornapudi, S. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00530 · Cited by 17
“Deep learning based object detection [7, 41, 42] and segmentation [9, 19] models are increasingly important in agri-culture for tasks like phenotyping [58, 61, 62], monitoring [4, 6], pest detection [1, 8], yield estimation [11, 24], etc. Due to the vast diversity of the agricultural domain, unique…”
Deep-Learning-Empowered Super Resolution: A Comprehensive Survey and Future Prospects
Zhang, L., Li, A., Hou, Q., Zhu, C., & Eldar, Y. C. (2025) · Proceedings of the IEEE · doi:10.1109/jproc.2025.3613233 · Cited by 23
“1) Convolutional Neural Network: CNN [79], [80], [81], [82], [83], [84], [85] is a DL model widely used for image analysis and computer vision tasks.”
Dong, F., & Wang, M. (2025) · Remote Sensing · doi:10.3390/rs17203497 · Cited by 12
“Owing to the superior capacity for visual feature extraction, CNN-based models (e.g., Fast-RCNN [5], YOLO [6], and Faster-RCNN [7]) have been widely adopted in wildfire detection tasks [8,9].”
Elaborate Information Refinement Network for Fine-Grained Object Detection in Remote Sensing Images
Sun, J., Yang, X., & Yang, D. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3624695 · Cited by 10
Deep Learning for Student Behavior Detection in Smart Classroom Environments
Wang, J., Sun, Y., & Tian, S. (2025) · Information · doi:10.3390/info16110949 · Cited by 19
Cotton leaf disease detection model focusing on small targets and comprehensive feature extraction
Abudukelimu, H., Zhang, G., Abulizi, A., Ye, J., Musideke, M., Shi, Y., & Awudan, G. (2025) · Scientific Reports · doi:10.1038/s41598-025-24898-5 · Cited by 13
“Classic object detection models, such as YOLO (You Only Look Once) 11 , not only provide precise recognition in complex environments but also enhance detection accuracy and speed through various model improvements, effectively meeting the requirements for real-time monitoring.”
Optimized YOLOv8s framework with deformable convolution for underwater object detection
Wang, X., Li, K., Fan, F., Wu, Y., & Zhang, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-28989-1 · Cited by 10
Towards autonomous photogrammetric forest inventory using a lightweight under-canopy robotic drone
Karjalainen, V., Koivumäki, N., Hakala, T., Muhojoki, J., Hyyppä, E., George, A., Suomalainen, J. M., & Honkavaara, E. (2025) · International Journal of Remote Sensing · doi:10.1080/01431161.2025.2579803 · Cited by 16
SAR-NanoShipNet: A scale-adaptive network for robust small ship detection in SAR imagery
Zhang, Y., Chi, J., Yang, G., Chen, C., & Yu, T. (2025) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2025.12.006 · Cited by 19
Zheng, K., Yang, S., Song, S., Gao, Y., Wang, X., Zou, W., Zhai, C., & Chen, L. (2026) · Agronomy · doi:10.3390/agronomy16020210 · Cited by 12
An improved YOLOv11 network for marine debris detection in underwater environment
Yuanwei, J., YiJiang, D., Xuemei, W., et al. (2026) · Scientific Reports · doi:10.1038/s41598-026-38305-0 · Cited by 9
He, Y., Gao, G., Xia, Z., He, D., Yang, G., Zhang, X., & Li, G. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3676397 · Cited by 14
OShipNet: Occlusion Ship Detection Based on Multidomain Fusion and Multiscale Refinement
Yang, S., Luo, H., Xu, Z., Yang, J., & Zhang, W. (2026) · Journal of Marine Science and Engineering · doi:10.3390/jmse14090804 · Cited by 12
MWNet: object detection network applicable for different weather conditions
Liu, P., Yuan, X., & Dai, X. (2019) · IET Intelligent Transport Systems · doi:10.1049/iet-its.2019.0023 · Cited by 8
Cascade marker removal algorithm for thyroid ultrasound images
Ying, X., Zhang, Y., Yu, M., Wei, X., Zhu, J., Gao, J., Liu, Z., Shen, H., Zhang, R., Li, X., et al. (2020) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-020-02216-7 · Cited by 11
Jiang, S., Wu, F., Yung, K. L., Yang, Y., Ip, W. H., Gao, M. Y., & Foster, J. A. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107562 · Cited by 10
Vehicle Tracking with Crop-based Detection
Gloudemans, D., & Work, D. B. (2021) · International Conference on Machine Learning and Applications · doi:10.1109/icmla52953.2021.00055 · Cited by 13
Scene images and text information‐based object location of robot grasping
Liu, Z., Ding, K., Xu, Q., Song, Y. H., Yuan, X., & Li, Y. (2022) · IET Cyber-Systems and Robotics · doi:10.1049/csy2.12049 · Cited by 12
Sign-to-Speech Model for Sign Language Understanding: A Case Study of Nigerian Sign Language
Kolawole, S., Osakuade, O., Saxena, N., & Olorisade, B. K. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/855 · Cited by 12
Ghiță, A. Ș., & Florea, A. M. (2022) · Sensors · doi:10.3390/s22155856 · Cited by 11
Deng, T., Liu, X., & Mao, G. (2022) · Electronics · doi:10.3390/electronics11172657 · Cited by 12
Improved Visual SLAM Using Semantic Segmentation and Layout Estimation
Mahmoud, A., & Atia, M. M. (2022) · Robotics · doi:10.3390/robotics11050091 · Cited by 8
Vishal, M. K., Saluja, R., Aggrawal, D., Banerjee, B., Raju, D., Kumar, S., Chinnusamy, V., Sahoo, R. N., & Jagarlapudi, A. (2022) · Plants · doi:10.3390/plants11192663 · Cited by 11
SYGNet: A SVD-YOLO based GhostNet for Real-time Driving Scene Parsing
Wang, H., Zhu, B., Li, Y., et al. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897534 · Cited by 9
Clipping-Based Post Training 8-Bit Quantization of Convolution Neural Networks for Object Detection
Chen, L., & Lou, P. (2022) · Applied Sciences · doi:10.3390/app122312405 · Cited by 9
Metadata
- 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
- 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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.