Enhanced YOLOv8s with Multi-Teacher Distillation for Steel Cord Ply Defect Detection
Applied Sciences · 13.04.2026 · 16 (8) · 3795
DOI: 10.3390/app16083795 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 13.04.2026. Verfasst von Peng Huang und 6 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangxi Key Research and Development Program, Guangxi Science and Technology Program.
Abstract (Originalsprache)
To improve detection accuracy for color-sensitive and small-target defects in steel cord ply, this paper introduces an improved YOLOv8s algorithm using multi-teacher stepwise hierarchical knowledge distillation for better adaptation across production lines. The improvements include: replacing the initial backbone convolutional layer with RGBV grouped convolution to enhance color feature extraction; substituting the SPPF module with SPPFCSPC-LSKA to improve multi-scale perception; and optimizing bounding box accuracy with the WIoU loss function. The multi-teacher distillation approach first transfers color feature learning using an RGBV-only teacher, then multi-scale feature learning with an SPPFCSPC-LSKA-only teacher. Experimental results show the improved model achieved 90.4% precision, 92.0% recall, 91.2% F1-score, and 97.2% mAP@0.5, surpassing the baseline YOLOv8s by 1.9, 2.2, 2.1, and 3.4 percentage points, respectively. The proposed model also achieves an inference time of 3.9 ms, representing a 1.0 ms reduction compared to the baseline. On a smaller dataset from another production line, single-teacher distillation increased precision, recall, F1-score, and mAP@0.5 to 84.6%, 82.0%, 83.3%, and 88.8%, respectively, albeit with an increase in inference time. The multi-teacher strategy further increased metrics to 97.5% precision, 88.8% recall, 92.9% F1-score, and 94.3% mAP@0.5, providing additional gains over single-teacher distillation while maintaining the same parameter count of 11.127 M and achieving a faster inference time of 4.1 ms on the target production line.
Förderung
- Guangxi Key Research and Development Program
- Guangxi Science and Technology Program
Zitieren
APA
Huang, P., Xie, Z., Long, R., Zhou, F., Zhang, X., Ke, Z., & Huang, G. (2026). Enhanced YOLOv8s with Multi-Teacher Distillation for Steel Cord Ply Defect Detection. Applied Sciences, 16(8), 3795. https://doi.org/10.3390/app16083795
Vancouver
Huang P, Xie Z, Long R, Zhou F, Zhang X, Ke Z, et al. Enhanced YOLOv8s with Multi-Teacher Distillation for Steel Cord Ply Defect Detection. Applied Sciences. 2026;16(8):3795. doi:10.3390/app16083795
BibTeX
@article{Huang2026,
author = {Huang, Peng and Xie, Zhongyi and Long, Rui and Zhou, Feiqiang and Zhang, Xinlong and Ke, Zejie and Huang, Guangzhan},
title = {Enhanced YOLOv8s with Multi-Teacher Distillation for Steel Cord Ply Defect Detection},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {8},
pages = {3795},
doi = {10.3390/app16083795}
}
EUVIMED