Enhancing Fabric Defect Detection Using Efficient Pyramid Split Attention in a Lightweight YOLOv5 Framework

Fabric defect detection is a fundamental quality control process in textile manufacturing, yet achieving accurate and reliable automated inspection remains difficult because of complex background textures, subtle defect patterns, and substantial variation in defect scale and shape. Although deep learning–based detectors have improved inspection performance, many lightweight models still suffer from limited feature discrimination, particularly in real-time industrial environments where computational efficiency is critical. To address this limitation, this study proposes an enhanced fabric defect detection framework by integrating an Efficient Pyramid Split Attention (EPSA) mechanism into a YOLOv5-based convolutional network. The EPSA module is designed to adaptively recalibrate multi-scale feature responses, enabling the network to emphasize defect-relevant information more effectively while preserving inference efficiency. A quantitative experimental design was employed using a labeled fabric defect image dataset, and the proposed model was evaluated through comparative and ablation analyses against baseline and alternative attention-based configurations. Experimental results indicate that the EPSA-enhanced model achieves superior detection performance in terms of mean Average Precision while maintaining real-time processing capability. The improvement is especially evident for small, low-contrast, and irregular defects embedded in repetitive fabric textures. These findings confirm that pyramid-based attention can substantially improve feature representation without imposing significant computational overhead. The proposed approach offers a practical and efficient solution for automated textile inspection and provides a useful foundation for future research on lightweight attention modeling for industrial vision systems.

fabric defect detection; attention mechanism; EPSA; convolutional neural networks

1. X. Xie, “A review of recent advances in surface defect detection using texture analysis techniques,” Electronic Letters on Computer Vision and Image Analysis, vol. 7, no. 3, pp. 1–22, 2008, doi: 10.5565/rev/elcvia.108. [Google Scholar] [Crossref]

2. Y. Liu, K. Zhang, J. Zhang, and Q. Wang, “Automatic fabric defect detection using convolutional neural networks,” Textile Research Journal, vol. 89, no. 23–24, pp. 5147–5160, 2019, doi: 10.1177/0040517519849985. [Google Scholar] [Crossref]

3. Kumar, “Computer-vision-based fabric defect detection: A survey,” IEEE Transactions on Industrial Electronics, vol. 55, no. 1, pp. 348–363, Jan. 2008, doi: 10.1109/TIE.2007.896476. [Google Scholar] [Crossref]

4. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015, doi: 10.1038/nature14539. [Google Scholar] [Crossref]

5. J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018. [Google Scholar] [Crossref]

6. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 779–788, doi: 10.1109/CVPR.2016.91. [Google Scholar] [Crossref]

7. G. Jocher et al., “YOLOv5,” GitHub repository, 2020. [Online]. Available: https://github.com/ultralytics/yolov5 [Google Scholar] [Crossref]

8. S. Woo, J. Park, J.-Y. Lee, and I. S. Kweon, “CBAM: Convolutional block attention module,” in Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 2018, pp. 3–19, doi: 10.1007/978-3-030-01234-2_1. [Google Scholar] [Crossref]

9. J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 2018, pp. 7132–7141, doi: 10.1109/CVPR.2018.00745. [Google Scholar] [Crossref]

10. T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 2117–2125, doi: 10.1109/CVPR.2017.106. [Google Scholar] [Crossref]

11. X. Wang, R. Girshick, A. Gupta, and K. He, “Non-local neural networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 2018, pp. 7794–7803, doi: 10.1109/CVPR.2018.00813. [Google Scholar] [Crossref]

12. H. Zhang, C. Wu, Z. Zhang, Y. Zhu, Z. Lin, and Y. Sun, “ResNeSt: Split-attention networks,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020, pp. 2736–2746, doi: 10.1109/CVPR42600.2020.00281. [Google Scholar] [Crossref]

13. Z. Zhu, H. Liang, H. Zhang, and R. Zhang, “Efficient pyramid split attention for convolutional neural networks,” Pattern Recognition, vol. 123, Art. no. 108377, 2022, doi: 10.1016/j.patcog.2021.108377. [Google Scholar] [Crossref]

14. Szegedy et al., “Going deeper with convolutions,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 1–9, doi: 10.1109/CVPR.2015.7298594. [Google Scholar] [Crossref]

15. International Organization for Standardization, Textiles—Quality Control and Inspection Systems, Geneva, Switzerland: ISO, 2015. [Google Scholar] [Crossref]

• Investigating the Performance of Colour Oxide on the PS/CNSO Oil Paint Production
• Real-Time Fabric Defect Detection Using a Lightweight Deformable YOLO Network
• Recent Trends in the Stock Market: An Analytical Study of Market Dynamics, Investor Behaviour, and Technological Influence
• Evaluation of Structural Dynamics and Equilibrium State, with Case Study of Large Cantilever Projection for a 10- Storey Reinforced Concrete Building in Lagos, Nigeria.
• Multi-Criteria Evaluation of AI-Based Adaptive Learning Platforms in Global Higher Education: A Fuzzy AHP Perspective