The DOI matches its Crossref record; 97 of the 103 references it cites were found in a registry or an index.
YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors
Open accessAbstract
Real-time object detection is one of the most important research topics in computer vision. As new approaches regarding architecture optimization and training optimization are continually being developed, we have found two research topics that have spawned when dealing with these latest state-of-the-art methods. To address the topics, we propose a trainable bag-of-freebies oriented solution. We combine the flexible and efficient training tools with the proposed architecture and the compound scaling method. YOLOv7 surpasses all known object detectors in both speed and accuracy in the range from 5 FPS to 120 FPS and has the highest accuracy 56.8% AP among all known real-time object detectors with 30 FPS or higher on GPU V100. Source code is released in https://github.com/WongKinYiu/yolov7.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“After pre-training with Objects365, RTDETR-R50 / R101 achieves 55 . 3% / 56 . 2% AP.”
From DETRs Beat YOLOs on Real-time Object Detection (2024) · cites this paper as [35]
In the citing paper
“Experimental results show that RT-DETR-R18/50/101 is improved by 2 . 7% / 2 . 2% / 1 . 9% AP on COCO val2017 .”
From DETRs Beat YOLOs on Real-time Object Detection (2024) · cites this paper as [35]
In the citing paper
“Experimental results show that RT-DETR-R18/50/101 is improved by 2 . 7% / 2 . 2% / 1 . 9% AP on COCO val2017 .”
From DETRs Beat YOLOs on Real-time Object Detection (2024) · cites this paper as [35]
In the citing paper
“Experimental results show that RT-DETR-R18/50/101 is improved by 2 . 7% / 2 . 2% / 1 . 9% AP on COCO val2017 .”
From DETRs Beat YOLOs on Real-time Object Detection (2024) · cites this paper as [35]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 3×
“Although RepConv [13] has achieved excellent performance on the VGG [68], when we directly apply it to ResNet [26] and DenseNet [32] and other architectures, its accuracy will be significantly reduced.”
MethodVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 2×
“Although RepConv [12] has achieved excellent performance on the VGG [65], when we directly apply it to ResNet [25] and DenseNet [31] and other nonplain architectures, its accuracy will be significantly reduced.”
MethodYou Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803 · cited 3×
“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…”
MethodDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566 · cited 7×
“Even for architectures such as ResNet [26] and DenseNet [32] which usually converge well, deep supervision [70, 98, 67, 47, 82, 65, 86, 50] can still significantly improve the performance of the model on many tasks.”
MethodInfluentialGoing 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 · cited 1×
“Even for architectures such as ResNet [26] and DenseNet [32] which usually converge well, deep supervision [70, 98, 67, 47, 82, 65, 86, 50] can still significantly improve the performance of the model on many tasks.”
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138 · cited 1×
“Model re-parametrization techniques [71, 31, 75, 19, 33, 11, 4, 24, 13, 12, 10, 29, 14, 78] merge multiple computational modules into one at inference stage.”
MethodMobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755
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 · cited 1×
“Currently state-of-the-art real-time object detectors are mainly based on YOLO [61, 62, 63] and FCOS [76, 77], which are [3, 79, 81, 21, 54, 85, 23].”
MethodMobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015 · cited 2×
“As for real-time object detectors that can be used on CPU [51, 81, 82, 86], their design is mostly based on MobileNet [26, 27, 63], ShuffleNet [52, 89], or GhostNet [24].”
MethodEnd-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
YOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141 · cited 2×
“Another real-time object detectors are developed for GPU [20, 79, 94], they mostly use ResNet [25], DarkNet [60], or DLA [85], and then use the CSPNet [77] strategy to optimize the architecture.”
MethodEfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, M., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1905.11946 · Cited by 17,072 · cited 1×
“For example the scaling model of EfficientNet [69] considers the width, depth, and resolution.”
MethodA Multi-Modal Distributed Real-Time IoT System for Urban Traffic Control (Invited Paper)
Khanam, Z., Achari, V. P. S., Boukhennoufa, I., et al. (2024) · Durham Research Online (Durham University) · doi:10.4230/oasics.ng-res.2024.2 · Cited by 14,048
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
Zhou, Z., Siddiquee, M. M. R., Tajbakhsh, N., & Liang, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00889-5_1 · Cited by 11,109
YOLOv4: 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
Self-citationShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00716 · Cited by 9,982 · cited 1×
“As for real-time object detectors that can be used on CPU [54, 88, 84, 83], their design is mostly based on MobileNet [28, 66, 27], ShuffleNet [92, 55], or GhostNet [25].”
MethodEfficientDet: Scalable and Efficient Object Detection
Tan, M., Pang, R., & Le, Q. V. (2019) · arXiv · Cited by 9,841 · cited 1×
“Being able to become a stateof-the-art real-time object detector usually requires the following characteristics: (1) a faster and stronger network architecture; (2) a more effective feature integration method [8, 21, 29, 36, 43, 56, 71, 94]; (3) a more accurate detection method [66, 73, 74]; (4) a more robust loss fun…”
MethodHoward, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., Pang, R., et al. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00140 · Cited by 9,708 · cited 2×
“As for real-time object detectors that can be used on CPU [54, 88, 84, 83], their design is mostly based on MobileNet [28, 66, 27], ShuffleNet [92, 55], or GhostNet [25].”
MethodShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Ma, N., Zhang, X., Zheng, H.-T., & Sun, J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01264-9_8 · Cited by 7,356
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 · cited 2×
“Currently state-of-the-art real-time object detectors are mainly based on YOLO [61, 62, 63] and FCOS [76, 77], which are [3, 79, 81, 21, 54, 85, 23].”
MethodGeneralized 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
Deformable DETR: Deformable Transformers for End-to-End Object Detection
Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2020) · arXiv · doi:10.48550/arxiv.2010.04159 · Cited by 6,027
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., & Ren, D. (2019) · arXiv · doi:10.48550/arxiv.1911.08287 · Cited by 5,313
Distance-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 · cited 1×
“Being able to become a stateof-the-art real-time object detector usually requires the following characteristics: (1) a faster and stronger network architecture; (2) a more effective feature integration method [8, 21, 29, 36, 43, 56, 71, 94]; (3) a more accurate detection method [66, 73, 74]; (4) a more robust loss fun…”
MethodCSPNet: A New Backbone that can Enhance Learning Capability of CNN
Wang, C.-Y., Mark Liao, H.-Y., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., & Yeh, I.-H. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00203 · Cited by 5,265
Self-citationGhostNet: More Features From Cheap Operations
Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., & Xu, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00165 · Cited by 5,222 · cited 2×
“As for real-time object detectors that can be used on CPU [54, 88, 84, 83], their design is mostly based on MobileNet [28, 66, 27], ShuffleNet [92, 55], or GhostNet [25].”
MethodTarvainen, A., & Valpola, H. (2017) · arXiv · doi:10.48550/arxiv.1703.01780 · Cited by 4,275
ByteTrack: Multi-object Tracking by Associating Every Detection Box
Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., & Wang, X. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20047-2_1 · Cited by 3,040 · cited 1×
“For example, multi-object tracking [90, 91], autonomous driving [17, 39], robotics [34, 55], medical image analysis [33, 44], etc.”
BackgroundSwin Transformer V2: Scaling Up Capacity and Resolution
Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., et al. (2022) · 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/cvpr52688.2022.01170 · Cited by 2,985
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 · cited 14×
“YOLOv7-E6 object detector (56 FPS V100, 55.9% AP) outperforms both transformer-based detector SWIN-L Cascade-Mask R-CNN (9.2 FPS A100, 53.9% AP) by 509% in speed and 2% in accuracy, and convolutional-based detector ConvNeXt-XL Cascade-Mask R-CNN (8.6 FPS A100, 55.2% AP) by 551% in speed and 0.7% AP in accuracy, as wel…”
MethodInfluentialRepVGG: Making VGG-style ConvNets Great Again
Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., & Sun, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01352 · Cited by 2,907 · cited 7×
“Recently, model re-parameterization [11, 12, 28] and dynamic label assignment [16, 19, 40] have become important topics in network training and object detection.”
BackgroundMethodInfluentialSwin Transformer V2: Scaling Up Capacity and Resolution
Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., et al. (2021) · arXiv · doi:10.48550/arxiv.2111.09883 · Cited by 2,679
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 2,614 · cited 1×
“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…”
MethodNAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
Ghiasi, G., Lin, T.-Y., & Le, Q. V. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00720 · Cited by 2,099
Designing Network Design Spaces
Radosavovic, I., Kosaraju, R. P., Girshick, R., He, K., & Dollar, P. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01044 · Cited by 2,084 · cited 1×
“Model scaling [72, 60, 74, 73, 15, 16, 2, 51] is a way to scale up or down an already designed model and make it fit in different computing devices.”
BackgroundFairMOT: On the Fairness of Detection and Re-identification in Multiple Object Tracking
Zhang, Y., Wang, C., Wang, X., Zeng, W., & Liu, W. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-021-01513-4 · Cited by 1,861 · cited 1×
“For example, multi-object tracking [90, 91], autonomous driving [17, 39], robotics [34, 55], medical image analysis [33, 44], etc.”
BackgroundSelf-citationScaled-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 1,820 · cited 5×
“In addition to considering the aforementioned basic designing concerns, the architecture of CSPVoVNet [79] also analyzes the gradient path, in order to enable the weights of different layers to learn more diverse features.”
BackgroundMethodInfluentialSelf-citationEfficientNetV2: Smaller Models and Faster TrainingPreprint
Tan, M., & Le, Q. V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.00298 · Cited by 1,725 · cited 1×
“Model scaling [72, 60, 74, 73, 15, 16, 2, 51] is a way to scale up or down an already designed model and make it fit in different computing devices.”
BackgroundDeeply-Supervised NetsPreprint
Lee, C., Xie, S., Gallagher, P., Zhang, Z., & Tu, Z. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1409.5185 · Cited by 1,693 · cited 1×
“Deep supervision [38] is a technique that is often used in training deep networks.”
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 · cited 3×
“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…”
BackgroundMethodYu, F., Wang, D., Shelhamer, E., & Darrell, T. (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.2018.00255 · Cited by 1,623 · cited 1×
“Another mainstream real-time object detectors are developed for GPU [81, 21, 97], they mostly use ResNet [26], DarkNet [63], or DLA [87], and then use the CSPNet [80] strategy to optimize the architecture.”
MethodSparse 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 · cited 1×
“Being able to become a state-of-the-art real-time object detector usually requires the following characteristics: (1) a faster and stronger network architecture; (2) a more effective feature integration method [22, 97, 37, 74, 59, 30, 9, 45]; (3) a more accurate detection method [76, 77, 69]; (4) a more robust loss fu…”
MethodSelf-citationScaling Up Your Kernels to 31×31: Revisiting Large Kernel Design in CNNs
Ding, X., Zhang, X., Han, J., & Ding, G. (2022) · 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/cvpr52688.2022.01166 · Cited by 1,592 · cited 1×
“Model re-parametrization techniques [71, 31, 75, 19, 33, 11, 4, 24, 13, 12, 10, 29, 14, 78] merge multiple computational modules into one at inference stage.”
MethodPanoptic Feature Pyramid Networks
Kirillov, A., Girshick, R., He, K., & Dollár, P. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00656 · Cited by 1,460 · cited 1×
“Being able to become a state-of-the-art real-time object detector usually requires the following characteristics: (1) a faster and stronger network architecture; (2) a more effective feature integration method [22, 97, 37, 74, 59, 30, 9, 45]; (3) a more accurate detection method [76, 77, 69]; (4) a more robust loss fu…”
MethodFeng, 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 · cited 1×
“For example, multi-object tracking [94, 93], autonomous driving [40, 18], robotics [35, 58], medical image analysis [34, 46], etc.”
BackgroundVarifocalNet: An IoU-aware Dense Object Detector
Zhang, H., Wang, Y., Dayoub, F., & Sünderhauf, N. (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/cvpr46437.2021.00841 · Cited by 1,307
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
Qiao, S., Chen, L.-C., & Yuille, A. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01008 · Cited by 1,245
Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection
Li, X., Wang, W., Wu, L., Chen, S., Hu, X., Li, J., Tang, J., & Yang, J. (2020) · arXiv · doi:10.48550/arxiv.2006.04388 · Cited by 1,241 · cited 1×
“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…”
MethodDynamic Head: Unifying Object Detection Heads with Attentions
Dai, X., Chen, Y., Xiao, B., Chen, D., Liu, M., Yuan, L., & Zhang, L. (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/cvpr46437.2021.00729 · Cited by 1,170 · cited 1×
“Being able to become a state-of-the-art real-time object detector usually requires the following characteristics: (1) a faster and stronger network architecture; (2) a more effective feature integration method [22, 97, 37, 74, 59, 30, 9, 45]; (3) a more accurate detection method [76, 77, 69]; (4) a more robust loss fu…”
MethodDINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L. M., & Shum, H.-Y. (2022) · arXiv · Cited by 1,154
Exploring Plain Vision Transformer Backbones for Object Detection
Li, Y., Mao, H., Girshick, R., & He, K. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20077-9_17 · Cited by 1,027
ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
Ding, X., Guo, Y., Ding, G., & Han, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00200 · Cited by 999 · cited 1×
“Model re-parametrization techniques [71, 31, 75, 19, 33, 11, 4, 24, 13, 12, 10, 29, 14, 78] merge multiple computational modules into one at inference stage.”
MethodFCOS: A Simple and Strong Anchor-free Object Detector
Tian, Z., Shen, C., Chen, H., & He, T. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3032166 · Cited by 972 · cited 3×
“Being able to become a stateof-the-art real-time object detector usually requires the following characteristics: (1) a faster and stronger network architecture; (2) a more effective feature integration method [8, 21, 29, 36, 43, 56, 71, 94]; (3) a more accurate detection method [66, 73, 74]; (4) a more robust loss fun…”
MethodVision Transformer Adapter for Dense PredictionsPreprint
Chen, Z., Duan, Y., Wang, W., He, J.-J., Lu, T., Dai, J.-F., & Qiao, Y. (2022) · International Conference on Learning Representations · doi:10.48550/arxiv.2205.08534 · Cited by 959
Averaging Weights Leads to Wider Optima and Better GeneralizationPreprint
Izmailov, P., Podoprikhin, D. A., Garipov, T., Vetrov, D., & Wilson, A. G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.05407 · Cited by 818
Snapshot Ensembles: Train 1, get M for freePreprint
Huang, G. M., Li, Y., Pleiss, G., Liu, Z., Hopcroft, J. E., & Weinberger, K. Q. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.00109 · Cited by 816 · cited 1×
“Model re-parametrization techniques [71, 31, 75, 19, 33, 11, 4, 24, 13, 12, 10, 29, 14, 78] merge multiple computational modules into one at inference stage.”
MethodOTA: Optimal Transport Assignment for Object Detection
Ge, Z., Liu, S., Li, Z., Yoshie, O., & Sun, J. (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/cvpr46437.2021.00037 · Cited by 580 · cited 3×
“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…”
BackgroundMethodDiverse Branch Block: Building a Convolution as an Inception-like Unit
Ding, X., Zhang, X., Han, J., & Ding, G. (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/cvpr46437.2021.01074 · Cited by 578 · cited 2×
“Model re-parametrization techniques [71, 31, 75, 19, 33, 11, 4, 24, 13, 12, 10, 29, 14, 78] merge multiple computational modules into one at inference stage.”
BackgroundMethodProbabilistic Anchor Assignment with IoU Prediction for Object Detection
Kim, K., & Lee, H. S. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58595-2_22 · Cited by 544 · cited 1×
“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…”
MethodAn Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection
Lee, Y., Hwang, J., Lee, S., Bae, Y., & Park, J. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00103 · Cited by 542 · cited 4×
“The design of CSPVoVNet [79] in Figure 2 (b) is a variation of VoVNet [39].”
MethodInfluentialIoU Loss for 2D/3D Object Detection
Zhou, D., Fang, J., Song, X., Guan, C., Yin, J., Dai, Y., & Yang, R. (2019) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00019 · Cited by 506 · cited 1×
“Being able to become a state-of-the-art real-time object detector usually requires the following characteristics: (1) a faster and stronger network architecture; (2) a more effective feature integration method [22, 97, 37, 74, 59, 30, 9, 45]; (3) a more accurate detection method [76, 77, 69]; (4) a more robust loss fu…”
MethodChoi, J., Chun, D., Kim, H., & Lee, H.-J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00059 · Cited by 505 · cited 1×
“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…”
MethodXiang, L., Wang, W., Hu, X., Li, J., Tang, J., & Yang, J. J. (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/cvpr46437.2021.01146 · Cited by 490 · cited 1×
“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…”
MethodMCUNet: Tiny Deep Learning on IoT DevicesPreprint
Lin, J., Chen, W.-M., Lin, Y., Cohn, J., Gan, C., & Han, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.10319 · Cited by 467 · cited 2×
“For example, the devel-Figure opment of MCUNet [49, 48] and NanoDet [54] focused on producing low-power single-chip and improving the inference speed on edge CPU.”
BackgroundYou Only Learn One Representation: Unified Network for Multiple TasksPreprint
Wang, C.-Y., Yeh, I.-H., & Liao, H.-Y. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.04206 · Cited by 383 · cited 5×
“As for methods such as YOLOX [20] and YOLOR [79], they focus on improving the inference speed of various GPUs.”
BackgroundMethodInfluentialSelf-citationEnsemble deep learning in bioinformatics
Cao, Y., Geddes, T. A., Yang, J. Y. H., & Yang, P. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-0217-y · Cited by 366 · cited 1×
“Model re-parametrization techniques [71, 31, 75, 19, 33, 11, 4, 24, 13, 12, 10, 29, 14, 78] merge multiple computational modules into one at inference stage.”
MethodGS3D: An Efficient 3D Object Detection Framework for Autonomous Driving
Li, B., Ouyang, W., Sheng, L., Zeng, X., & Wang, X. (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.2019.00111 · Cited by 365 · cited 1×
“For example, multi-object tracking [94, 93], autonomous driving [40, 18], robotics [35, 58], medical image analysis [34, 46], etc.”
BackgroundPP-YOLOE: An evolved version of YOLOPreprint
Xu, S., Wang, X., Lv, W., Chang, Q., Cui, C., Deng, K., Wang, G., Dang, Q., Wei, S., Du, Y., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.16250 · Cited by 301 · cited 3×
“We find that the design of RepCSPResNet [85] also fit our design pattern.”
MethodRevisiting ResNets: Improved Training and Scaling StrategiesPreprint
Bello, I., Fedus, W., Du, X., Cubuk, E. D., Srinivas, A., Lin, T.-Y., Shlens, J., & Zoph, B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.07579 · Cited by 280
AutoAssign: Differentiable Label Assignment for Dense Object DetectionPreprint
Zhu, B., Wang, J., Jiang, Z., Zong, F., Liu, S., Li, Z., & Sun, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.03496 · Cited by 274 · cited 1×
“Being able to become a stateof-the-art real-time object detector usually requires the following characteristics: (1) a faster and stronger network architecture; (2) a more effective feature integration method [8, 21, 29, 36, 43, 56, 71, 94]; (3) a more accurate detection method [66, 73, 74]; (4) a more robust loss fun…”
MethodLoss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
Garipov, T., Izmailov, P., Podoprikhin, D., Vetrov, D., & Wilson, A. G. (2018) · arXiv · doi:10.48550/arxiv.1802.10026 · Cited by 252 · cited 1×
“Model re-parametrization techniques [71, 31, 75, 19, 33, 11, 4, 24, 13, 12, 10, 29, 14, 78] merge multiple computational modules into one at inference stage.”
MethodSparse DETR: Efficient End-to-End Object Detection with Learnable SparsityPreprint
Roh, B., Shin, J., Shin, W., & Kim, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.14330 · Cited by 246 · cited 1×
“Even for architectures such as ResNet [26] and DenseNet [32] which usually converge well, deep supervision [70, 98, 67, 47, 82, 65, 86, 50] can still significantly improve the performance of the model on many tasks.”
End-to-End Object Detection with Fully Convolutional Network
Wang, J., Song, L., Li, Z., Sun, H., Sun, J., & Zheng, N. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01559 · Cited by 235 · cited 2×
“Even for architectures such as ResNet [26] and DenseNet [32] which usually converge well, deep supervision [70, 98, 67, 47, 82, 65, 86, 50] can still significantly improve the performance of the model on many tasks.”
MethodCBNet: A Composite Backbone Network Architecture for Object Detection
Liang, T., Chu, X., Liu, Y., Wang, Y., Tang, Z., Chu, W., Chen, J., & Ling, H. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3216771 · Cited by 218
CLU-CNNs: Object detection for medical images
Li, Z., Dong, M., Wen, S., Hu, X. Y., Zhou, P., & Zeng, Z. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.04.028 · Cited by 205 · cited 1×
“For example, multi-object tracking [94, 93], autonomous driving [40, 18], robotics [35, 58], medical image analysis [34, 46], etc.”
BackgroundMobileDets: Searching for Object Detection Architectures for Mobile Accelerators
Xiong, Y., Liu, H., Gupta, S., Akin, B., Bender, G., Wang, Y., Kindermans, P.-J., Tan, M., Singh, V., & Chen, B. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00382 · Cited by 193 · cited 4×
“The computing devices that execute real-time object detection is usually some mobile CPU or GPU, as well as various neural processing units (NPU) developed by major manufacturers.”
MethodInfluentialDesigning Network Design Strategies Through Gradient Path AnalysisPreprint
Wang, C.-Y., Liao, H.-Y. M., & Yeh, I.-H. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.04800 · Cited by 183
Self-citationA2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation
Hu, M., Li, Y., Fang, L., & Wang, S. (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/cvpr46437.2021.01509 · Cited by 155 · cited 1×
“Being able to become a state-of-the-art real-time object detector usually requires the following characteristics: (1) a faster and stronger network architecture; (2) a more effective feature integration method [22, 97, 37, 74, 59, 30, 9, 45]; (3) a more accurate detection method [76, 77, 69]; (4) a more robust loss fu…”
MethodA Dual Weighting Label Assignment Scheme for Object Detection
Li, S., He, C., Li, R., & Zhang, L. (2022) · 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/cvpr52688.2022.00917 · Cited by 138 · cited 3×
“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…”
BackgroundMethodObject Detection Approach for Robot Grasp Detection
Karaoğuz, H., & Jensfelt, P. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793751 · Cited by 125 · cited 1×
“For example, multi-object tracking [94, 93], autonomous driving [40, 18], robotics [35, 58], medical image analysis [34, 46], etc.”
BackgroundFast and Accurate Model Scaling
Dollár, P., Singh, M., & Girshick, R. (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/cvpr46437.2021.00098 · Cited by 122 · cited 3×
“In [15], the researcher analyzes the relationship between scaling factors and the amount of parameters and operations, trying to directly estimate some rules, and thereby obtain the scaling factors required by model scaling.”
BackgroundMethod3D-MAN: 3D Multi-frame Attention Network for Object Detection
Yang, Z., Zhou, Y., Chen, Z., & Ngiam, J. (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/cvpr46437.2021.00190 · Cited by 117 · cited 1×
“Even for architectures such as ResNet [26] and DenseNet [32] which usually converge well, deep supervision [70, 98, 67, 47, 82, 65, 86, 50] can still significantly improve the performance of the model on many tasks.”
PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices
Yu, G., Chang, Q., Lv, W., Xu, C., Cui, C., Ji, W., Dang, Q., Deng, K., Wang, G., Du, Y., et al. (2021) · arXiv · doi:10.48550/arxiv.2111.00902 · Cited by 112
Object Detection from Scratch with Deep Supervision
Shen, Z., Liu, Z., Li, J., Jiang, Y., Chen, Y., & Xue, X. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2922181 · Cited by 109 · cited 1×
“Even for architectures such as ResNet [26] and DenseNet [32] which usually converge well, deep supervision [70, 98, 67, 47, 82, 65, 86, 50] can still significantly improve the performance of the model on many tasks.”
Online Convolutional Reparameterization
Hu, M. H., Feng, J., Hua, J., Lai, B., Huang, J., Gong, X., & Hua, X. (2022) · 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/cvpr52688.2022.00065 · Cited by 107
Jaeger, P. F., Köhl, S., Bickelhaupt, S., Isensee, F., Kuder, T. A., Schlemmer, H., & Maier-Hein, K. H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.08661 · Cited by 97
YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection
Liu, Y., Wang, L., & Liu, M. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561423 · Cited by 90 · cited 1×
“Even for architectures such as ResNet [26] and DenseNet [32] which usually converge well, deep supervision [70, 98, 67, 47, 82, 65, 86, 50] can still significantly improve the performance of the model on many tasks.”
AP-Loss for Accurate One-Stage Object Detection
Chen, K., Lin, W., Li, J., See, J., Wang, J., & Zou, J. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2991457 · Cited by 87 · cited 1×
“Being able to become a state-of-the-art real-time object detector usually requires the following characteristics: (1) a faster and stronger network architecture; (2) a more effective feature integration method [22, 97, 37, 74, 59, 30, 9, 45]; (3) a more accurate detection method [76, 77, 69]; (4) a more robust loss fu…”
MethodRank & Sort Loss for Object Detection and Instance Segmentation
Öksüz, K., Çam, B. C., Akbaş, E., & Kalkan, S. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00300 · Cited by 54 · cited 1×
“Being able to become a state-of-the-art real-time object detector usually requires the following characteristics: (1) a faster and stronger network architecture; (2) a more effective feature integration method [22, 97, 37, 74, 59, 30, 9, 45]; (3) a more accurate detection method [76, 77, 69]; (4) a more robust loss fu…”
MethodExpandNets: Linear Over-parameterization to Train Compact Convolutional NetworksPreprint
Guo, S., Álvarez, J. M., & Salzmann, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.10495 · Cited by 49
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object DetectionPreprint
Öksüz, K., Çam, B. C., Akbaş, E., & Kalkan, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.13592 · Cited by 38 · cited 1×
“Being able to become a stateof-the-art real-time object detector usually requires the following characteristics: (1) a faster and stronger network architecture; (2) a more effective feature integration method [8, 21, 29, 36, 43, 56, 71, 94]; (3) a more accurate detection method [66, 73, 74]; (4) a more robust loss fun…”
MethodMemory-efficient Patch-based Inference for Tiny Deep Learning
Lin, J., Chen, W.-M., Cai, H., Gan, C., & Han, S. (2021) · neural information processing systems · Cited by 38
Re-parameterizing Your Optimizers rather than Architectures
Ding, X., Chen, H., Zhang, X., Huang, K., Han, J., & Ding, G. (2022) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · doi:10.48550/arxiv.2205.15242 · Cited by 33
Paul, S. K., Chowdhury, M. T., Nicolescu, M., Nicolescu, M. N., & Feil-Seifer, D. (2021) · Transactions on computational science and computational intelligence · doi:10.1007/978-3-030-71051-4_10 · Cited by 32 · cited 1×
“For example, multi-object tracking [94, 93], autonomous driving [40, 18], robotics [35, 58], medical image analysis [34, 46], etc.”
BackgroundFBNetV5: Neural Architecture Search for Multiple Tasks in One RunPreprint
Wu, B., Li, C., Zhang, H., Dai, X., Zhang, P., Yu, M., Wang, J., Lin, Y., & Vajda, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.10007 · Cited by 32 · cited 4×
“The computing devices that execute real-time object detection is usually some mobile CPU or GPU, as well as various neural processing units (NPU) developed by major manufacturers.”
MethodInfluentialSimple Training Strategies and Model Scaling for Object DetectionPreprint
Du, X., Zoph, B., Hung, W.-C., & Lin, T.-Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.00057 · Cited by 28 · cited 1×
“Model scaling [72, 60, 74, 73, 15, 16, 2, 51] is a way to scale up or down an already designed model and make it fit in different computing devices.”
Background
Research works printed but not linked: 5
- lyu, 2021, NanoDet-Plus
- glenn, 2022, Yolov5 Release v6 1
- hu, 0, Online convolutional re-parameterization, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- zhou, 2019, Objects as points, ArXiv Preprint
- kumar, 2022, An improved one millisecond mobile backbone, ArXiv Preprint
Cited by
Sorted by citations
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
“We utilize the benchmark to test the end-to-end speed of anchor-based detectors YOLOv5 [10] and YOLOv7 [35], as well as anchor-free detectors PP-YOLOE [37], YOLOv6 [15] and YOLOv8 [11] on T4 GPU with TensorRT FP16.”
BackgroundMethodInfluentialYOLOv9: 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
Self-citationObject 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
“Recently, YOLOv7 [52], a follow-up work from YOLOv4 team, has been proposed.”
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 4,118
ByteTrack: Multi-object Tracking by Associating Every Detection Box
Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., & Wang, X. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20047-2_1 · Cited by 3,040
Metadata
- Authors
- Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M.
- Affiliations
- Institute of Information Science, Academia Sinica (TW)
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 7464-7475
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386076325
- Cited by
- 13,198
- References
- 103
- Citations by year
- 2026: 1908 · 2025: 4113 · 2024: 4600 · 2023: 2384
- FWCI
- 1392.15
- 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)
- Funders
- NCHC
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- YOLOv7, real-time object detection, compound scaling, architecture optimization, detection speed and accuracy
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.
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
