A lightweight fabric defect detection with parallel dilated convolution and dual attention mechanism
PeerJ Computer Science · 21.08.2025 · 11 · e3136
DOI: 10.7717/peerj-cs.3136 ↗Kurz gefasst
Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 21.08.2025. Verfasst von Zheqing Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Big Data and Artificial Intelligence, Chizhou University, Chizhou, Anhui, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Research Key Project of Department of Education Anhui Province, China.
Abstract (Originalsprache)
Detecting defects in fabrics is essential to quality control in the manufacturing process of textile productions. To increase detection efficiency, a variety of automatic fabric defect detections have been developed. However, most of these methods rely on complex model with heavy parameters, leading to high computational costs that hinder their adaptation to real-time detection environments. To overcome these obstacles, we proposed a lightweight fabric defect detection (Light-FDD), building upon the You Only Look Once v8 Nano (YOLOv8n) framework with further optimizations. Specifically, the backbone employed an improved FasterNet architecture for feature extraction. In order to capture multi-scale contextual information, we designed a parallel dilated convolution downsampling (PDCD) block to replace the conventional downsampling block in the backbone. In addition, a novel dual attention mechanism, called the global context and receptive-filed (GCRF) attention, was presented to help the model focus on key regions. Furthermore, a lightweight cross-stage partial (CSP) layer was deployed by dual convolution for feature fusion, reducing redundant parameters to further lighten the model. Results from extensive experiments on public fabric defect datasets showed that Light-FDD outperforms existing state-of-the-art lightweight models in terms of detection accuracy while requiring low computational cost. The present study suggests that the performance and effectiveness of detection models can be balanced through the adoption of reasonable strategies.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Big Data and Artificial Intelligence, Chizhou University, Chizhou, Anhui, China.
- School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, Anhui, China.
Förderung
- Natural Science Research Key Project of Department of Education Anhui Province, China
Zitieren
APA
Zhang, Z., Lu, K., & Yang, G. (2025). A lightweight fabric defect detection with parallel dilated convolution and dual attention mechanism. PeerJ Computer Science, 11, e3136. https://doi.org/10.7717/peerj-cs.3136
Vancouver
Zhang Z, Lu K, Yang G. A lightweight fabric defect detection with parallel dilated convolution and dual attention mechanism. PeerJ Computer Science. 2025;11:e3136. doi:10.7717/peerj-cs.3136
BibTeX
@article{Zhang2025,
author = {Zhang, Zheqing and Lu, Kezhong and Yang, Gaoming},
title = {A lightweight fabric defect detection with parallel dilated convolution and dual attention mechanism},
journal = {PeerJ Computer Science},
year = {2025},
volume = {11},
pages = {e3136},
doi = {10.7717/peerj-cs.3136}
}
EUVIMED