CoChat
Sign Up
Cited by 313Industrial Vision Systems and Defect DetectionAdvanced Neural Network ApplicationsInfrastructure Maintenance and Monitoring

MSFT-YOLO: Improved YOLOv5 Based on Transformer for Detecting Defects of Steel Surface

Open access
Guo, Zexuan, Wang, Chensheng, Yang, Guang, Huang, Zeyuan, Li, Guo·2022·Sensors
DOI 10.3390/s22093467PMC PMC9100565
Open this paper in CoChat — free accountOpen PDF

Abstract

With the development of artificial intelligence technology and the popularity of intelligent production projects, intelligent inspection systems have gradually become a hot topic in the industrial field. As a fundamental problem in the field of computer vision, how to achieve object detection in the industry while taking into account the accuracy and real-time detection is an important challenge in the development of intelligent detection systems. The detection of defects on steel surfaces is an important application of object detection in the industry. Correct and fast detection of surface defects can greatly improve productivity and product quality. To this end, this paper introduces the MSFT-YOLO model, which is improved based on the one-stage detector. The MSFT-YOLO model is proposed for the industrial scenario in which the image background interference is great, the defect category is easily confused, the defect scale changes a great deal, and the detection results of small defects are poor. By adding the TRANS module, which is designed based on Transformer, to the backbone and detection headers, the features can be combined with global information. The fusion of features at different scales by combining multi-scale feature fusion structures enhances the dynamic adjustment of the detector to objects at different scales. To further improve the performance of MSFT-YOLO, we also introduce plenty of effective strategies, such as data augmentation and multi-step training methods. The test results on the NEU-DET dataset show that MSPF-YOLO can achieve real-time detection, and the average detection accuracy of MSFT-YOLO is 75.2, improving about 7% compared to the baseline model (YOLOv5) and 18% compared to Faster R-CNN, which is advantageous and inspiring.

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/s22093467

Cites

7 of 7 references verified0 citation errors · 0 not checkable

Statistics

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

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?

Self-check

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

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

Cites

Flagged first, then by citations

Research works printed but not linked: 26

  1. [4]Redmon J. Farhadi A. YOLO9000: Better, Faster, Stronger arXiv 2016 1612.08242
  2. [5]Redmon J. Farhadi A. YOLOv3: An Incremental Improvement arXiv 2018 1804.02767
  3. [6]Bochkovskiy A. Wang C.Y. Liao H. YOLOv4: Optimal speed and accuracy of object detection arXiv 2020 2004.10934
  4. [7]Girshick R. Donahue J. Darrell T. Malik T. Region-Based Convolutional Networks for Accurate object Detection and Segmentation IEEE Trans. Pattern Anal. Mach. Intell. 2016 38 142 158 10.1109/TPAMI.2015.2437384 26656583 · DOI · Paper page
  5. [8]Girshick R. Fast R-CNN arXiv 2015 1504.08083
  6. [9]Ren S. He K. Girshick R. Sun J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks Proceedings of the 28th International Conference on Neural Information Processing Systems Montreal, QC, Canada 7–12 December 2015
  7. [10]Simonyan K. Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition arXiv 2014 1409.1556
  8. [13]Dosovitskiy A. Beyer L. Kolesnikov A. Weissenborn D. Zhai X. Unterthiner T. Houlsby N. An Image is Worth 16 × 16 Words: Transformers for Image Recognition at Scale arXiv 2020 2010.11929
  9. [14]Naseer M. Ranasinghe K. Khan S.H. Hayat M. Shahbaz Khan F. Yang M.H. Intriguing Properties of Vision Transformers Proceedings of the NIPS 2012: Neural Information Processing Systems Conference Lake Tahoe, NV, USA 3–6 December 2012
  10. [15]Luo C. Yu L. Yan J. Li Z. Ren P. Bai B. Yang E. Liu Y. Autonomous detection of damage to multiple steel surfaces from 360° panoramas using deep neural networks Comput.-Aided Civ. Infrastruct. Eng. 2021 36 1585 1599 10.1111/mice.12686 · DOI
  11. [16]Zhang H. Wang Y. Dayoub F. Sunderhauf N. VarifocalNet: An IoU-aware Dense Object Detector Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Nashville, TN, USA 20–25 June 2021
  12. [17]Zhou X. Koltun V. Krhenbühl P. Probabilistic two-stage detection arXiv 2021 2103.07461
  13. [18]Munawar H.S. Hammad A.W. Haddad A. Soares C.A.P. Waller S.T. Image-based crack detection methods: A review Infrastructures 2021 6 115 10.3390/infrastructures6080115 · DOI
  14. [19]Ge Z. Liu S. Wang F. Li Z. Sun J. YOLOX: Exceeding YOLO Series in 2021 arXiv 2021 2107.08430
  15. [20]Tian Z. Shen C. Chen H. He T. FCOS: A simple and strong anchor-free object detector IEEE Trans. Pattern Anal. Mach. Intell. 2020 44 1922 1933 10.1109/TPAMI.2020.3032166 33074804 · DOI
  16. [21]Zhu X. Su W. Lu L. Li B. Wang X. Dai J. Deformable DETR: Deformable Transformers for End-to-End Object Detection arXiv 2010 2010.04159
  17. [22]Wang C.Y. Bochkovskiy A. Liao H. Scaled-YOLOv4: Scaling Cross Stage Partial Network arXiv 2020 2011.08036
  18. [24]Liu S. Qi L. Qin H. Shi J. Jia J. Path Aggregation Network for Instance Segmentation Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City UT, USA 28–23 June 2018
  19. [25]Vaswani A. Shazeer N. Parmar N. Uszkoreit J. Jones L. Gomez A.N. Kaiser L. Polosukhin I. Attention Is All You Need arXiv 2017 1706.03762
  20. [26]Ghiasi G. Lin T.Y. Le Q.V. NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Long Beach, CA, USA 15–20 June 2019
  21. [27]Liu S. Huang D. Wang Y. Learning Spatial Fusion for Single-Shot Object Detection arXiv 2019 1911.09516
  22. [28]Ch En P.Y. Ch Ang M.C. Hsieh J.W. Wang C.Y. Liao H.Y.M. Gochoo M. Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection IEEE Trans. Image Processing 2019 1911 12051 34735334
  23. [29]Kong T. Sun F. Huang W. Tan C. Liu H. Deep Feature Pyramid Reconfiguration for Object Detection Proceedings of the European Conference on Computer Vision (ECCV) Munich, Germany 8–14 September 2018 169 185
  24. [30]Zhao Q. Sheng T. Wang Y. Tang Z. Chen Y. Cai L. Ling H. M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network Proceedings of the AAAI conference on Artificial Intelligence Virtual 3–4 February 2018
  25. [31]Zhang H. Cisse M. Dauphin Y.N. Lopez-Paz D. Mixup: Beyond Empirical Risk Minimization arXiv 2017 1710.09412
  26. [32]Huang L. Zhang C. Zhang H. Self-adaptive training: Beyond empirical risk minimization Adv. Neural Inf. Processing Syst. 2020 33 19365 19376

Cited by

Sorted by citations

Authors
Guo, Z., Wang, C., Yang, G., Huang, Z., & Li, G.
Affiliations
Beijing University of Posts and Telecommunications (CN)
Corresponding author
Wang, Chensheng
ORCID
Venue
Sensors
Publisher
MDPI AG
Published
2022-05-02
Volume
22
Issue
9
Pages
3467
ISSN
1424-8220 (ISSN-L)
DOI
10.3390/s22093467
PMC
PMC9100565
OpenAlex
W4225321635
Cited by
313
References
7
Citations by year
2026: 48 · 2025: 81 · 2024: 96 · 2023: 68 · 2022: 20
FWCI
30.41
Type
journal article
Language
en
Open access
Licence
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Provincial Key Research and Development Plan (BE2016032, BE2010019)
  • Major Scientific and Technological Support and Independent Innovation Project (BE2016032, BE2010019)
Topics
  • Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
Keywords
steel surface defect detection, YOLOv5, transformer models, one-stage object detection, multi-scale feature fusion, small object detection, industrial visual inspection, real-time detection, NEU-DET dataset

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