A context-aware progressive attention aggregation network for fabric defect detection

Abstract

Fabric defect detection plays a critical role for measuring quality control in the textile manufacturing industry. Deep learning-based saliency models can quickly spot the most interesting regions that attract human attention from the complex background, which have been successfully applied in fabric defect detection. However, most of the previous methods mainly adopted multi-level feature aggregation yet ignored the complementary relationship among different features, and thus resulted in poor representation capability for the tiny and slender defects. To remedy these issues, we propose a novel saliency-based fabric defect detection network, which can exploit the complementary information between different layers to enhance the representation features ability and discrimination of defects. Specifically, a multi-scale feature aggregation unit (MFAU) is proposed to effectively characterize the multi-scale contextual features. Besides, a feature fusion refinement module (FFR) composed of an attention fusion unit (AFU) and an auxiliary refinement unit (ARU) is designed to exploit complementary important information and further refine the input features for enhancing the discriminative ability of defect features. Finally, a multi-level deep supervision (MDS) is adopted to guide the model to generate more accurate saliency maps. Under different evaluation metrics, our proposed method outperforms most state-of-the-art methods on our developed fabric datasets.

YOLOvT: CSPNet-based attention for a lightweight textile defect detection model

“…Lu et al 16 performed partial defect removal and restoration on defective fabric images, generating defect-free images, and then inputting both the restored and original images into a detection network for defect detection and segmentation. Liu et al 17 introduced a multi-scale feature aggregation unit and feature fusion refinement module to effectively represent multi-scale background features, strengthening the complementary relationships between different features, and demonstrated excellent performance on their self-made dataset. Wang et al 18 improved YOLOv5 using bidirectional feature fusion pyramid and CA attention mechanisms, achieving a 2.3% accuracy increase over the baseline network on their selfmade dataset.…”

“…Liu et al. 17 introduced a multi-scale feature aggregation unit and feature fusion refinement module to effectively represent multi-scale background features, strengthening the complementary relationships between different features, and demonstrated excellent performance on their self-made dataset. Wang et al.…”