CoChat
Sign Up
Cited by 13,198Advanced Neural Network ApplicationsDomain Adaptation and Few-Shot LearningVisual Attention and Saliency Detection

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 access
Wang, Chien-Yao, Bochkovskiy, Alexey, Liao, Hong-Yuan Mark·2023·2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr52729.2023.00721
Open this paper in CoChat — free accountOpen PDF

Abstract

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

Crossref · 10.1109/cvpr52729.2023.00721

Cites

97 of 97 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

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.”
    Method

  • Very 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.”
    Method

  • You 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…”
    Method

  • Densely 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.”
    MethodInfluential

  • Going 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.”
    Method

  • MobileNetV2: 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].”
    Method

  • MobileNets: 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].”
    Method

Show all 103 references

Research works printed but not linked: 5

  1. lyu, 2021, NanoDet-Plus
  2. glenn, 2022, Yolov5 Release v6 1
  3. hu, 0, Online convolutional re-parameterization, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  4. zhou, 2019, Objects as points, ArXiv Preprint
  5. kumar, 2022, An improved one millisecond mobile backbone, ArXiv Preprint

Cited by

Sorted by citations

Related

See all

Metadata

Authors
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M.
Affiliations
Institute of Information Science, Academia Sinica (TW)
ORCID
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)
DOI
10.1109/cvpr52729.2023.00721
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
Licence
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