YOLO-MAD: Multi-Scale Geometric Structure Feature Extraction and Fusion for Steel Surface Defect Detection
Source abstract
Abstract
Lightweight visual models are crucial for industrial defect detection tasks. Traditional methods and even some lightweight detectors often struggle with the trade-off between high computational demands and insufficient accuracy. To overcome these issues, this study introduces YOLO-MAD, an innovative model optimized through a multi-scale geometric structure feature extraction and fusion scheme. YOLO-MAD integrates three key modules: AKConv for robust geometric feature extraction, BiFPN to facilitate effective multi-scale feature integration, and Detect_DyHead for dynamic optimization of detection capabilities. Empirical evaluations demonstrate significant performance improvements: YOLO-MAD achieves a 5.4% mAP increase on the NEU-DET dataset and a 4.8% mAP increase on the GC10-DET dataset. Crucially, this is achieved under a moderate computational load (9.4 GFLOPs), outperforming several prominent lightweight models in detection accuracy while maintaining comparable efficiency. The model also shows enhanced recognition performance for most defect categories. This work presents a pioneering approach that balances lightweight design with high detection performance by efficiently leveraging multi-scale geometric feature extraction and fusion, offering a new paradigm for industrial defect detection.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Advanced Neural Network Applications · Infrastructure Maintenance and Monitoring
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China
References (47)
Show source-provided references
1. Surface Defect Detection Methods for Industrial Products: A Review10.3390/app11167657 ↗
2. A Review of Metal Surface Defect Detection Technologies in Industrial Applications10.1109/ACCESS.2025.3544578 ↗
3. Automated recognition of surface defects using digital color image processing10.1016/j.autcon.2005.08.001 ↗
4. Rattanaphan, S., and Briassouli, A. (2024). Evaluating Generalization, Bias, and Fairness in Deep Learning for Metal Surface Defect Detection: A Comparative Study. Processes, 12.10.3390/pr12030456 ↗
5. Steel surface defect detection algorithm in complex background scenarios10.1016/j.measurement.2024.115189 ↗
6. Recent advances in surface defect inspection of industrial products using deep learning techniques10.1007/s00170-021-06592-8 ↗
7. A Review of Yolo Algorithm Developments10.1016/j.procs.2022.01.135 ↗
8. Efficient Steel Surface Defect Detection via a Lightweight YOLO Framework with Task-Specific Knowledge-Guided Optimization10.3390/electronics14102029 ↗
9. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
10. Ultralytics (2025, May 10). Ultralytics YOLO. Available online: https://docs.ultralytics.com/.
11. Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv.
12. Jocher, G. (2025, May 10). YOLOv5 by Ultralytics. Available online: https://github.com/ultralytics/yolov5.
13. Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2023, January 17–24). YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.00721 ↗
14. Varghese, R., and Sambath, M. (2024, January 18–19). YOLOv8: A Novel Object Detection Algorithm with Enhanced Performance and Robustness. Proceedings of the 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), Chennai, India.10.1109/ADICS58448.2024.10533619 ↗
15. Jocher, G., Chaurasia, A., and Qiu, J. (2025, May 10). YOLO by Ultralytics. Available online: https://github.com/ultralytics/ultralytics.
16. Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., and Wei, Y. (2017, January 22–29). Deformable Convolutional Networks. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.89 ↗
17. Ouyang, D., He, S., Zhang, G., Luo, M., Guo, H., Zhan, J., and Huang, Z. (2023, January 4–10). Efficient Multi-Scale Attention Module with Cross-Spatial Learning. Proceedings of the ICASSP 2023—2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece.10.1109/ICASSP49357.2023.10096516 ↗
18. Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., and Xu, C. (2020, January 13–19). GhostNet: More Features from Cheap Operations. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00165 ↗
19. Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018, January 18–23). ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00716 ↗
20. FMV-YOLO: A Steel Surface Defect Detection Algorithm for Real-World Scenarios10.3390/electronics14061143 ↗
21. WSS-YOLO: An improved industrial defect detection network for steel surface defects10.1016/j.measurement.2024.115060 ↗
22. Ren, S., He, K., Girshick, R., and Sun, J. (2025, January 7–12). Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. Proceedings of the 29th International Conference on Neural Information Processing Systems, Montreal, QC, Canada.
23. He, K., Gkioxari, G., Dollar, P., and Girshick, R. (2017, January 22–29). Mask R-CNN. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.322 ↗
24. Zhang, G., Cui, K., Hung, T.Y., and Lu, S. (2021, January 3–8). Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection. Proceedings of the 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.10.1109/WACV48630.2021.00257 ↗
25. Contrastive self-supervised representation learning framework for metal surface defect detection10.1186/s40537-023-00827-z ↗
26. Multimodal Fusion Convolutional Neural Network with Cross-Attention Mechanism for Internal Defect Detection of Magnetic Tile10.1109/ACCESS.2022.3180725 ↗
27. Zhang, X., Song, Y., Song, T., Yang, D., Ye, Y., Zhou, J., and Zhang, L. (2023). AKConv: Convolutional Kernel with Arbitrary Sampled Shapes and Arbitrary Number of Parameters. arXiv.
28. Tan, M., Pang, R., and Le, Q.V. (2020, January 13–19). EfficientDet: Scalable and Efficient Object Detection. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.01079 ↗
29. Dai, X., Chen, Y., Xiao, B., Chen, D., Liu, M., Yuan, L., and Zhang, L. (2021, January 20–25). Dynamic Head: Unifying Object Detection Heads with Attentions. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.00729 ↗
30. Real-Time Steel Surface Defect Detection with Improved Multi-Scale YOLO-v510.3390/pr11051357 ↗
31. Improved Steel Surface Defect Detection Algorithm Based on YOLOv810.1109/ACCESS.2024.3429555 ↗
32. Zhang, H., Li, S., Miao, Q., Fang, R., Xue, S., Hu, Q., Hu, J., and Chan, S. (2024). Surface defect detection of hot rolled steel based on multi-scale feature fusion and attention mechanism residual block. Sci. Rep., 14.10.1038/s41598-024-57990-3 ↗
33. ADD-YOLO: A new model for object detection in aerial images10.1007/s00530-025-01688-7 ↗
34. Triplet-graph reasoning network for few-shot metal generic surface defect segmentation10.1109/TIM.2021.3083561 ↗
35. A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects10.1016/j.apsusc.2013.09.002 ↗
36. An end-to-end steel surface defect detection approach via fusing multiple hierarchical features10.1109/TIM.2019.2915404 ↗
37. Lv, X., Duan, F., Jiang, J.j., Fu, X., and Gan, L. (2020). Deep metallic surface defect detection: The new benchmark and detection network. Sensors, 20.10.3390/s20061562 ↗
38. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11–14). SSD: Single shot multibox detector. Proceedings of the Computer Vision—ECCV 2016: 14th European Conference, Amsterdam, The Netherlands. Proceedings, Part I 14.10.1007/978-3-319-46448-0_2 ↗
39. Ma, X., Deng, X., Kuang, H., and Liu, X. (2024, January 24–26). YOLOv7-BA: A Metal Surface Defect Detection Model Based On Dynamic Sparse Sampling And Adaptive Spatial Feature Fusion. Proceedings of the 2024 IEEE 6th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), Chongqing, China.10.1109/IMCEC59810.2024.10575022 ↗
40. Guo, Z., Wang, C., Yang, G., Huang, Z., and Li, G. (2022). MSFT-YOLO: Improved YOLOv5 Based on Transformer for Detecting Defects of Steel Surface. Sensors, 22.10.3390/s22093467 ↗
41. Pang, J., Chen, K., Shi, J., Feng, H., Ouyang, W., and Lin, D. (2019, January 15–20). Libra r-cnn: Towards balanced learning for object detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00091 ↗
42. Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017, January 22–29). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.324 ↗
43. Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22–29). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.74 ↗
44. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
45. The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery10.1145/3236386.3241340 ↗
46. Shu, X., Xu, L., He, Z., Sheng, L., Ye, G., and Lu, X. (November, January 31). Wafer Defect Detection Based on YOLO-BA. Proceedings of the 2024 International Conference on Sensing, Measurement & Data Analytics in the Era of Artificial Intelligence (ICSMD), Huangshan, China.10.1109/ICSMD64214.2024.10920518 ↗
47. Jezek, S., Jonak, M., Burget, R., Dvorak, P., and Skotak, M. (2021, January 25–27). Deep learning-based defect detection of metal parts: Evaluating current methods in complex conditions. Proceedings of the 2021 13th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), Brno, Czech Republic.10.1109/ICUMT54235.2021.9631567 ↗