Fab-ME: A Vision State-Space and Attention-Enhanced Framework for Fabric Defect Detection

TL;DR

Fab-ME is a novel fabric defect detection framework that enhances YOLOv8s with a vision state-space module and multi-scale attention, achieving higher accuracy and better small defect sensitivity.

Contribution

The paper introduces a new framework combining vision state-space modeling and attention mechanisms into YOLOv8s for improved fabric defect detection.

Findings

Achieves 3.5% higher mAP@0.5 than YOLOv8s.

Effectively detects 20 fabric defect types.

Enhances detection of small defects.

Abstract

Effective defect detection is critical for ensuring the quality, functionality, and economic value of textile products. However, existing methods face challenges in achieving high accuracy, real-time performance, and efficient global information extraction. To address these issues, we propose Fab-ME, an advanced framework based on YOLOv8s, specifically designed for the accurate detection of 20 fabric defect types. Our contributions include the introduction of the cross-stage partial bottleneck with two convolutions (C2F) vision state-space (C2F-VMamba) module, which integrates visual state-space (VSS) blocks into the YOLOv8s feature fusion network neck, enhancing the capture of intricate details and global context while maintaining high processing speeds. Additionally, we incorporate an enhanced multi-scale channel attention (EMCA) module into the final layer of the feature extraction network, significantly improving sensitivity to small targets. Experimental results on the Tianchi fabric defect detection dataset demonstrate that Fab-ME achieves a 3.5% improvement in mAP@0.5 compared to the original YOLOv8s, validating its effectiveness for precise and efficient fabric defect detection.