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 13,801–13,900 of 51,399
Down-Sampling of Large LiDAR Dataset in the Context of Off-Road Objects Extraction
Błaszczak-Bąk, W., Janicka, J., Suchocki, C., et al. (2020) · Geosciences · doi:10.3390/geosciences10060219 · Cited by 14
Narrow-band Signal Localization for SETI on Noisy Synthetic Spectrogram Data
Brzycki, B., Siemion, A. P. V., Croft, S., et al. (2020) · Publications of the Astronomical Society of the Pacific · doi:10.1088/1538-3873/abaaf7 · Cited by 14
End-to-End Spatial Transform Face Detection and Recognition
Zhang, H., & Chi, L. (2020) · Virtual Reality & Intelligent Hardware · doi:10.1016/j.vrih.2020.04.002 · Cited by 19
Towards Fine-grained Sampling for Active Learning in Object Detection
Vikas Desai, S., & Balasubramanian, V. N. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00470 · Cited by 14
“State-of-the-art deep object detectors such as Faster RCNN [18], Feature Pyramid Networks [15], RetinaNet [16] and YOLO [17] have been shown to achieve excellent performance in visual object detection.”
A Multi-Class Objects Detection Coprocessor With Dual Feature Space and Weighted Softmax
Xiao, Z., Xu, P., Wang, X., Chen, L., & An, F. (2020) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2020.3010517 · Cited by 16
BOUNDARY REGULARIZED BUILDING FOOTPRINT EXTRACTION FROM SATELLITE IMAGES USING DEEP NEURAL NETWORKS
Zhao, K., Kamran, M., & Sohn, G. (2020) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-v-2-2020-617-2020 · Cited by 24
Collision Analysis to Motor Dashcam Videos With YOLO and Mask R-CNN for Auto Insurance
Hsu, H.-H., Huang, N.-F., & Han, C.-H. (2020) · International Conference on Intelligent Engineering and Management (ICIEM) · doi:10.1109/iciem48762.2020.9160263 · Cited by 14
Application of Transfer Learning in Infrared Pedestrian Detection
Hu, J., Zhao, Y., & Zhang, X. (2020) · IEEE International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc50857.2020.9177438 · Cited by 14
Boschi, A., Salvetti, F., Mazzia, V., & Chiaberge, M. (2020) · Machines · doi:10.3390/machines8030049 · Cited by 18
Dual Context-Aware Refinement Network for Person Search
Liu, J., Zha, Z.-J., Hong, R., Wang, M., & Zhang, Y. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413878 · Cited by 17
A Systematic Literature Review on Machine Learning in Object Detection Security
Alzaabi, A., Talib, M. A., Nassif, A. B., Sajwani, A., & Einea, O. (2020) · International Conference on Computing, Communication and Automation · doi:10.1109/iccca49541.2020.9250836 · Cited by 19
Structure-aware completion of photogrammetric meshes in urban road environment
Zhu, Q., Shang, Q., Hu, H., Yu, H., & Zhong, R. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.02.010 · Cited by 16
An Accelerated Prototype with Movidius Neural Compute Stick for Real-Time Object Detection
Kaarmukilan, S. P., Hazarika, A., Amal Thomas, K., Poddar, S., & Rahaman, H. (2020) · International Symposium on Devices, Circuits and Systems (ISDCS) · doi:10.1109/isdcs49393.2020.9262996 · Cited by 15
Multi-Camera-Based Person Recognition System for Autonomous Tractors
Jung, T.-H., Cates, B., Choi, I.-K., Lee, S., & Choi, J. (2020) · Designs · doi:10.3390/designs4040054 · Cited by 17
Utomo, W., Putrawan, P. W. B., Kurniawan, A. R., Juniastuti, S., & Yuniarno, E. M. (2020) · International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM) · doi:10.1109/cenim51130.2020.9297921 · Cited by 19
Toward Autonomous Garbage Collection Robots in Terrains with Different Elevations
Miyagusuku, R., Arai, Y., KAKIGI, Y., Takebayashi, T., Fukushima, A., & OZAKI, K. (2020) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2020.p1164 · Cited by 14
GRU-based capsule network with an improved loss for personnel performance prediction
Xue, X., Gao, Y. D., Liu, M., Sun, X., Zhang, W., & Feng, J. H. (2021) · Applied Intelligence · doi:10.1007/s10489-020-02039-x · Cited by 15
A semi-supervised deep convolutional framework for signet ring cell detection
Ying, H., Song, Q., Chen, J., Liang, T., Gu, J., Zhuang, F., Chen, D. Z., & Wu, J. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.05.119 · Cited by 15
Shivapakash, S., Jain, H., Hellwich, O., & Gerfers, F. (2021) · IEEE Open Journal of Circuits and Systems · doi:10.1109/ojcas.2020.3047225 · Cited by 17
Object-Aware Centroid Voting for Monocular 3D Object Detection
Bao, W., Yu, Q., & Kong, Y. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340889 · Cited by 14
Research on the Cascade Vehicle Detection Method Based on CNN
Hu, J., Sun, Y., & Xiong, S. (2021) · Electronics · doi:10.3390/electronics10040481 · Cited by 16
Feature pyramid of bi-directional stepped concatenation for small object detection
Zheng, Q., & Chen, Y. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10718-1 · Cited by 15
Gao, Q., & Shen, X. (2021) · Image and Vision Computing · doi:10.1016/j.imavis.2021.104161 · Cited by 14
2D Laser and 3D Camera Data Integration and Filtering for Human Trajectory Tracking
Bozorgi, H., Truong, X. T., La, H. M., et al. (2021) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/ieeeconf49454.2021.9382732 · Cited by 14
FPGA Implementation of a Binarized Dual Stream Convolutional Neural Network for Service Robots
Yoshimoto, Y., & Tamukoh, H. (2021) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2021.p0386 · Cited by 17
Learned Image Compression Using Adaptive Block-Wise Encoding and Reconstruction Network
Zhao, Z., Jia, C., Wang, S., Ma, S., & Yang, J. (2021) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas51556.2021.9401164 · Cited by 14
Combined person classification with airborne optical sectioning
Kurmi, I., Schedl, D. C., & Bimber, O. (2022) · Scientific Reports · doi:10.1038/s41598-022-07733-z · Cited by 20
Density Aware 3D Object Single Stage Detector
Ning, J., Da, F., & Gai, S. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3106302 · Cited by 16
Mask or Non-Mask? Robust Face Mask Detector via Triplet-Consistency Representation Learning
Yang, C., Phung, T. H., Shuai, H.-H., & Cheng, W.-H. (2022) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3472623 · Cited by 18
Secured Perimeter with Electromagnetic Detection and Tracking with Drone Embedded and Static Cameras
Teixidó, P., Galán, J., Caballero, R., et al. (2021) · Sensors · doi:10.3390/s21217379 · Cited by 14
GLE-Net: A Global and Local Ensemble Network for Aerial Object Detection
Liao, J., Liu, Y., Piao, Y., Su, J., Cai, G., & Wu, Y. (2022) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-021-00056-3 · Cited by 18
Liu, C., Yang, J., Ou, J., & Fan, D. (2022) · Remote Sensing · doi:10.3390/rs14071729 · Cited by 15
Optimization of Deep-Learning Detection of Humans in Marine Environment on Edge Devices
Rizk, M., Heller, D., Douguet, R., Baghdadi, A., & Diguet, J.-P. (2022) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs202256217.2022.9970780 · Cited by 19
Integrating Appearance and Spatial-Temporal Information for Multi-Camera People Tracking
Yang, W., Xie, Z., Wang, Y., Zhang, Y., Ma, X., & Hao, B. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00554 · Cited by 13
Faster R-CNN for Small Traffic Sign Detection
Zhang, Z. D., Zhou, X., Chan, S., Chen, S., & Liu, H. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-7305-2_14 · Cited by 14
Running 8-bit dynamic fixed-point convolutional neural network on low-cost ARM platforms
Peng, P., Mingyu, Y., & Xu, W. (2017) · Chinese Automation Congress · doi:10.1109/cac.2017.8243585 · Cited by 20
Table Analysis and Information Extraction for Medical Laboratory Reports
Xue, W., Li, Q., Zhang, Z., Zhao, Y., & Wang, H. (2018) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/dasc/picom/datacom/cyberscitec.2018.00043 · Cited by 14
Exploring the Design Space of Deep Convolutional Neural Networks at Large ScalePreprint
Iandola, F. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.06519 · Cited by 23
Zhang, X., Gu, N., Ye, H., & Lin, C. (2018) · Journal of Electronic Imaging · doi:10.1117/1.jei.27.4.043056 · Cited by 15
Underwater Fish Detection using Deep Learning for Water Power ApplicationsPreprint
Xu, W., & Matzner, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.01494 · Cited by 14
Universal Semi-Supervised Semantic SegmentationPreprint
Kalluri, T., Varma, G., Chandraker, M. K., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.10323 · Cited by 14
Clustered Object Detection in Aerial ImagesPreprint
Yang, F., Fan, H., Chu, P., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.08008 · Cited by 14
Efficient Object Detection Model for Real-Time UAV ApplicationsPreprint
Vaddi, S., Kumar, C., & Jannesari, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.00786 · Cited by 26
The Architectural Implications of Facebook's DNN-based Personalized RecommendationPreprint
Gupta, U., Wu, C.-J., Wang, X., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.03109 · Cited by 14
Fang, J., Zhou, L., & Liu, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.01867 · Cited by 21
Self-supervised 6D Object Pose Estimation for Robot ManipulationPreprint
Deng, X., Yu, X. J., Mousavian, A., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.10159 · Cited by 14
Generalization Bounds for Convolutional Neural NetworksPreprint
Lin, S., & Zhang, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.01487 · Cited by 40
Revisiting animal photo-identification using deep metric learning and network analysisPreprint
Miele, V., Dussert, G., Spataro, B., Chamaillé‐Jammes, S., Allainé, D., & Bonenfant, C. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.03.25.007377 · Cited by 14
A Close Look at Deep Learning with Small DataPreprint
Brigato, L., & Iocchi, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.12843 · Cited by 14
Hassan, T., Akçay, S., Bennamoun, M., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.06780 · Cited by 14
Dynamic Refinement Network for Oriented and Densely Packed Object DetectionPreprint
Pan, X., Ren, Y., Sheng, K., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.09973 · Cited by 14
Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object DetectionPreprint
Du, L., Ye, X., Tan, X., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.04356 · Cited by 14
Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNNPreprint
He, Z., & Zhang, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.01571 · Cited by 14
Attention Neural Network for Trash Detection on Water ChannelsPreprint
Tharani, M., Amin, A. W., Maaz, M., & Taj, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.04639 · Cited by 24
Analyzing Worldwide Social Distancing through Large-Scale Computer VisionPreprint
Ghodgaonkar, I., Chakraborty, S., Banna, V., Allcroft, S., Metwaly, M., Bordwell, F., Kimura, K., Zhao, X., Goel, A., Tung, C., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.12363 · Cited by 25
End-to-End Object Detection with Fully Convolutional NetworkPreprint
Wang, J., Song, L., Li, Z., Sun, H., Sun, J., & Zheng, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.03544 · Cited by 11
Automated Detection of Coronary Artery Stenosis in X-ray Angiography using Deep Neural NetworksPreprint
Rodrigues, D. L., Menezes, M. N., Pinto, F. J., & Oliveira, A. L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.02969 · Cited by 34
Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object DetectionPreprint
Hu, H., Bai, S., Li, A., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.17115 · Cited by 14
AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large ScenesPreprint
Xu, J., Li, Y., & Wang, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.10409 · Cited by 16
Dynamic Relevance Learning for Few-Shot Object DetectionPreprint
Liu, W., Wang, C., Li, H., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.02235 · Cited by 14
A Comparative Review of Recent Few-Shot Object Detection AlgorithmsPreprint
Leng, J., Taiyue, C., Gao, X., Yu, Y., Wang, Y., Gao, F., & Wang, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.00201 · Cited by 26
Small and Dim Target Detection in IR Imagery: A ReviewPreprint
Kumar, N., & Singh, P. P. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4854547 · Cited by 20
Kwon, H., Tong, C., Haresamudram, H., Gao, Y., Abowd, G. D., Lane, N. D., & Ploetz, T. (2020) · arXiv · doi:10.48550/arxiv.2006.05675 · Cited by 14
Deep Learning Approaches for Vehicle and Pedestrian Detection in Adverse Weather
Zaman, M., Saha, S., Zohrabi, N., & Abdelwahed, S. (2023) · 2023 IEEE Transportation Electrification Conference & Expo (ITEC) · doi:10.1109/itec55900.2023.10187020 · Cited by 13
EOGT: Video Anomaly Detection with Enhanced Object Information and Global Temporal Dependency
Pi, R., Wu, P., He, X., & Peng, Y. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3662185 · Cited by 16
Hsu, Y.-H., Yu, C.-C., & Cheng, H.-Y. (2024) · Sensors · doi:10.3390/s24134372 · Cited by 29
Chen, C., Wang, H., Pan, Y., et al. (2024) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-024-14482-y · Cited by 13
Li, X., Yang, Y., Sun, C., et al. (2024) · Sustainability · doi:10.3390/su16208954 · Cited by 13
CATrack: Condition-aware multi-object tracking with temporally enhanced appearance features
Wang, Y., Li, R., Zhang, D., Li, M., Cao, J., & Zheng, Z. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112760 · Cited by 16
YOLO-Wheat: A More Accurate Real-Time Detection Algorithm for Wheat Pests
Liu, Y., Wang, Q., Zheng, Q., & Liu, Y. (2024) · Agriculture · doi:10.3390/agriculture14122244 · Cited by 16
Gaussian Combined Distance: A Generic Metric for Object Detection
Guan, Z., Fu, X., Huang, P., Zhang, H., Du, H., Liu, Y., Wang, Y., & Ma, Q. (2025) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2025.3531970 · Cited by 26
“To mitigate the sensitivity of the L 2 -norm to the size of bounding boxes, YOLOv1 [20] introduced a square root transformation of bounding box dimensions to lessen the impact of larger boxes, while YOLOv3 [21] incorporated a penalty term to reduce their dominance.”
PJ-YOLO: Prior-Knowledge and Joint-Feature-Extraction Based YOLO for Infrared Ship Detection
Liu, Y., Li, C., & Fu, G. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13020226 · Cited by 13
A Banana Ripeness Detection Model Based on Improved YOLOv9c Multifactor Complex Scenarios
Wang, G., Gao, Y., Xu, F., Sang, W., Han, Y., & Liu, Q. (2025) · Symmetry · doi:10.3390/sym17020231 · Cited by 20
Chen, S., Gao, M., Shi, P., Zeng, X., & Zhang, A. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13020366 · Cited by 19
A novel generative model for brain tumor detection using magnetic resonance imaging
Nascimento, J. J. D. C., Marques, A. G., Souza, L. D. N., Dourado, C. M. J. D. M., Barros, A. C. D. S., de Albuquerque, V. H. C., & Sousa, L. F. D. F. (2025) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2025.102498 · Cited by 17
Liu, S., Shen, X., Xiao, S., Li, H., & Tao, H. (2025) · Remote Sensing · doi:10.3390/rs17061014 · Cited by 17
A computational method for real‐time roof defect segmentation in robotic inspection
Zhao, X., & Jebelli, H. (2025) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13471 · Cited by 22
Two-stage object detection in low-light environments using deep learning image enhancement
Al-refai, G., ElMoaqet, H., Al-Refai, A., Alzu’bi, A., Al-Hadhrami, T., & Alkhateeb, A. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.2799 · Cited by 20
Mao, G., Liang, H., Yao, Y., Wang, L., & Zhang, N. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3558929 · Cited by 18
IRWT-YOLO: A Background Subtraction-Based Method for Anti-Drone Detection
Cheng, X., Wang, F., Hu, X., Wu, X., & Nuo, M. (2025) · Drones · doi:10.3390/drones9040297 · Cited by 18
MI-DETR: A small object detection model for mixed scenes
Peng, B., Xiong, S., Wang, Y., Zhou, T., Li, J., Xiao, H., & Xiong, R. (2025) · Displays · doi:10.1016/j.displa.2025.103052 · Cited by 15
Zheng, H., Liu, C., Zhong, L., Wang, J., Huang, J., Lin, F., Ma, X., & Tan, S. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1561632 · Cited by 19
“One-stage networks, as RTMDet (Real-Time Multi-Scale Detection) (Zhang et al., 2023) and the YOLO series (Redmon et al., 2016), perform object detection directly.”
Xiao, B., & Hu, Y. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3564958 · Cited by 21
ST-YOLO: An Enhanced Detector of Small Objects in Unmanned Aerial Vehicle Imagery
Yan, H., Kong, X., Wang, J., & Tomiyama, H. (2025) · Drones · doi:10.3390/drones9050338 · Cited by 16
“Conversely, one-stage detection methods, exemplified by You Only Look Once (YOLO) [15], streamline the detection process by predicting target categories and locations in a single forward propagation step, without the need for generating candidate regions beforehand.”
Yang, L., Gu, Y., & Feng, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-99835-7 · Cited by 26
Real-Time Aerial Multispectral Object Detection with Dynamic Modality-Balanced Pixel-Level Fusion
Wang, Z., & Zhang, Q. (2025) · Sensors · doi:10.3390/s25103039 · Cited by 14
“One-stage methods, like SSD [29], Retinanet [30] and the YOLO [31] series, unify region proposal and classification into a single neural network, which are end-to-end architectures directly predicting bounding box coordinates and object classes.”
LDDFSF-YOLO11: A Lightweight Insulator Defect Detection Method Focusing on Small-Sized Features
Shen, P., Mei, K., Cao, H., Zhao, Y., & Zhang, G. (2025) · IEEE Access · doi:10.1109/access.2025.3569970 · Cited by 30
Mapping recreational marine traffic from Sentinel-2 imagery using YOLO object detection models
Mäyrä, J., Virtanen, E., Jokinen, A.-P., Koskikala, J., Väkevä, S., & Attila, J. (2025) · Remote Sensing of Environment · doi:10.1016/j.rse.2025.114791 · Cited by 25
Density-Aware DETR With Dynamic Query for End-to-End Tiny Object Detection
Ye, X., Xu, C., Zhu, H., Xu, F., Zhang, H., & Yang, W. T. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3571814 · Cited by 21
Liu, Y., Han, X., Ren, L., et al. (2025) · Agronomy · doi:10.3390/agronomy15051234 · Cited by 13
MEIS-YOLO: Improving YOLOv11 for Efficient Aerial Object Detection with Lightweight Design
Liu, Y. Y., Wu, J., & Chen, L. (2025) · Intelligent and Converged Networks · doi:10.23919/icn.2025.0010 · Cited by 16
LP-YOLO: An improved lightweight pedestrian detection algorithm based on YOLOv11
Qu, Z., Liu, H., Kong, W., Gu, J. J., Wang, C., Deng, L., Liu, L., & Lin, F. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105343 · Cited by 22
Building Surface Defect Detection Based on Improved YOLOv8
Lin, X., Meng, Y., Sun, L. J., Yang, X., Leng, C., Li, Y., Niu, Z., Gong, W., & Xiao, X. (2025) · Buildings · doi:10.3390/buildings15111865 · Cited by 21
RML-YOLO: An Insulator Defect Detection Method for UAV Aerial Images
Deng, Z., Li, X., & Yang, R. (2025) · Applied Sciences · doi:10.3390/app15116117 · Cited by 18
About Time: Advances, Challenges, and Outlooks of Action Understanding
Stergiou, A., & Poppe, R. W. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-025-02478-4 · Cited by 22
Li, J., Hua, Y., & Xue, M. (2025) · Electronics · doi:10.3390/electronics14122327 · Cited by 16
DGSS-YOLOv8s: A Real-Time Model for Small and Complex Object Detection in Autonomous Vehicles
Cheng, S., Chen, L., & Yang, K. (2025) · Algorithms · doi:10.3390/a18060358 · Cited by 21
HybridNets: End-to-End Perception Network
Dat, V. T., Bao, N. V. H., & Hung, P. D. (2025) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661825700038 · Cited by 155
Robot Manipulation Based on Embodied Visual Perception: A Survey
Wang, S., Nikolić, M. N., Lam, T. L., Gao, Q. H., Ding, R., & Zhang, T. (2025) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.70022 · Cited by 29
Enhanced YOLO11 for lightweight and accurate drone-based maritime search and rescue object detection
Zhao, B., Zhao, J., Song, R., Yu, L., Zhang, X., & Liu, J. (2025) · PLoS ONE · doi:10.1371/journal.pone.0321920 · Cited by 19
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.