DLSE-Net: A robust weakly supervised network for fabric defect detection

Abstract

The feasibility of deep convolutional neural network for fabric defect detection has been proven, but the detection performance often depends on large-scale labeled datasets. However, it is troublesome to collect large amounts of fabric defects with pixel-level labeling in industrial production. Although the weakly supervised detection methods can reduce the labeling workload, fabric defect detection is still a challenging task due to the slight difference between defects and complex texture backgrounds, and the diversity of defect types. To alleviate this issue, this paper proposes an effective weakly supervised shallow network, called DLSE-Net, with Link-SE (L-SE) module and Dilation Up-Weight CAM (DUW-CAM) for fabric defect detection. Firstly, the network regards a residual connection as a new branch to alleviate the semantic gap generated by the connection of different layers. Secondly, L-SE module forces the weights to be associated with the overall network in a global optimization manner instead of only within a single layer. Finally, a novel DUW-CAM with an attention mechanism is proposed to improve the adaptability of the network by combining dilated convolution and attention mechanism. Moreover, DUW-CAM can effectively suppress the background and highlight defect regions, even on complex fabric textures. Experimental results demonstrate that our proposed approach can localize the defects with high accuracy, and outperforms the state-of-the-art methods on two distinctive fabric datasets with different textures.