Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 3,052

The DOI matches its Crossref record; 104 of the 104 references it cites were found in a registry or an index.

A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS

Open access
Terven, Juan, Córdova-Esparza, Diana-Margarita, Romero-González, Julio-Alejandro·2023·Machine Learning and Knowledge Extraction
DOI 10.3390/make5040083
Open this paper in CoChat — free account

Abstract

YOLO has become a central real-time object detection system for robotics, driverless cars, and video monitoring applications. We present a comprehensive analysis of YOLO’s evolution, examining the innovations and contributions in each iteration from the original YOLO up to YOLOv8, YOLO-NAS, and YOLO with transformers. We start by describing the standard metrics and postprocessing; then, we discuss the major changes in network architecture and training tricks for each model. Finally, we summarize the essential lessons from YOLO’s development and provide a perspective on its future, highlighting potential research directions to enhance real-time object detection systems.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/make5040083

Cites

104 of 104 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 28

  1. Bhavya Sree, B., Yashwanth Bharadwaj, V., and Neelima, N. (2021). Intelligent Manufacturing and Energy Sustainability: Proceedings of ICIMES 2020, Springer.
  2. Benjumea, A., Teeti, I., Cuzzolin, F., and Bradley, A. (2021). YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles. arXiv.
  3. Kumar, P., Narasimha Swamy, S., Kumar, P., Purohit, G., and Raju, K.S. (2021). Data Analytics and Management: Proceedings of ICDAM, Springer.
  4. Kulik, S., and Shtanko, A. (2020). Advanced Technologies in Robotics and Intelligent Systems: Proceedings of ITR 2019, Springer.
  5. Maas, A.L., Hannun, A.Y., and Ng, A.Y. (2013, January 16). Rectifier nonlinearities improve neural network acoustic models. Proceedings of the 30th International Conference on Machine Learning, Atlanta, GA, USA.
  6. Lin, M., Chen, Q., and Yan, S. (2013). Network in network. arXiv.
  7. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
  8. Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv.
  9. Misra, D. (2019). Mish: A self-regularized non-monotonic neural activation function. arXiv.
  10. Islam, M.A., Naha, S., Rochan, M., Bruce, N., and Wang, Y. (2017). Label refinement network for coarse-to-fine semantic segmentation. arXiv.
  11. Loshchilov, I., and Hutter, F. (2016). Sgdr: Stochastic gradient descent with warm restarts. arXiv.
  12. Hendrycks, D., and Gimpel, K. (2016). Gaussian error linear units (gelus). arXiv.
  13. Long, X., Deng, K., Wang, G., Zhang, Y., Dang, Q., Gao, Y., Shen, H., Ren, J., Han, S., and Ding, E. (2020). PP-YOLO: An effective and efficient implementation of object detector. arXiv.
  14. Wang, C.Y., Yeh, I.H., and Liao, H.Y.M. (2021). You only learn one representation: Unified network for multiple tasks. arXiv.
  15. Ge, Z., Liu, S., Wang, F., Li, Z., and Sun, J. (2021). Yolox: Exceeding Yolo series in 2021. arXiv.
  16. Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., and Nie, W. (2022). Yolov6: A single-stage object detection framework for industrial applications. arXiv.
  17. Gevorgyan, Z. (2022). SIoU loss: More powerful learning for bounding box regression. arXiv.
  18. Ding, X., Chen, H., Zhang, X., Huang, K., Han, J., and Ding, G. (2022). Re-parameterizing Your Optimizers rather than Architectures. arXiv.
  19. Wang, C.Y., Liao, H.Y.M., and Yeh, I.H. (2022). Designing Network Design Strategies Through Gradient Path Analysis. arXiv.
  20. Xu, X., Jiang, Y., Chen, W., Huang, Y., Zhang, Y., and Sun, X. (2022). DAMO-YOLO: A Report on Real-Time Object Detection Design. arXiv.
  21. Li, 2020, Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection, Adv. Neural Inf. Process. Syst., 33, 21002
  22. Wang, X., Zhang, R., Kong, T., Li, L., and Shen, C. (2020, January 6–12). Solov2: Dynamic, faster and stronger. Proceedings of the Thirty-Fourth Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, BC, Canada.
  23. Huang, X., Wang, X., Lv, W., Bai, X., Long, X., Deng, K., Dang, Q., Han, S., Liu, Q., and Hu, X. (2021). PP-YOLOv2: A practical object detector. arXiv.
  24. Xu, S., Wang, X., Lv, W., Chang, Q., Cui, C., Deng, K., Wang, G., Dang, Q., Wei, S., and Du, Y. (2022). PP-YOLOE: An evolved version of YOLO. arXiv.
  25. Rao, L. (2021). TreeNet: A lightweight One-Shot Aggregation Convolutional Network. arXiv.
  26. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017). Advances in Neural Information Processing Systems, MIT Press.
  27. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv.
  28. Ouyang, H. (2022). DEYO: DETR with YOLO for Step-by-Step Object Detection. arXiv.

Cited by

See all 3,052

Metadata

Authors
Terven, J., Córdova-Esparza, D.-M., & Romero-González, J.-A.
Venue
Machine Learning and Knowledge Extraction
Publisher
MDPI AG
Published
2023-11-20
Volume
5
Issue
4
Pages
1680-1716
ISSN
2504-4990 (ISSN-L)
DOI
10.3390/make5040083
OpenAlex
W4388823657
Cited by
3,052
References
104
FWCI
277.67
Type
journal article
Language
en
Open access
gold
Licence
creativecommons.org/licenses/by/4.0/ (vor)
Funders
Instituto Politecnico Nacional (SIP 20232290)

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

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.