Attention-Gate-based U-shaped Reconstruction Network (AGUR-Net) for color-patterned fabric defect detection

Abstract

Color-patterned fabrics possess changeable patterns, low probability of defective samples, and various forms of defects. Therefore, the unsupervised inspection of color-patterned fabrics has gradually become a research hotspot in the field of fabric defect detection. However, due to the redundant information of skip connections in the network and the limitation of post-processing, the current reconstruction-based unsupervised fabric defect detection methods have difficulty in detecting some defects of color-patterned fabrics. In this article, we propose an Attention-Gate-based U-shaped Reconstruction Network (AGUR-Net) and a dual-threshold segmentation post-processing method. AGUR-Net consists of an encoder, an Atrous Spatial Pyramid Pooling module and an attention gate weighted fusion residual decoder. The encoder is used to obtain more representative features of the input image via EfficientNet-B2. The Atrous Spatial Pyramid Pooling module is used to enlarge the receptive field of the network and introduce multi-scale information into the decoder. The attention-gate-weighted residual fusion decoder is used to fuse the features of the encoder with the features of the decoder to obtain the reconstructed image. The dual-threshold segmentation post-processing is used to obtain the final defect detection results. Our method achieves a precision of 59.38%, a recall of 59.1%, an F1 of 54.31%, and an intersection-over-union ratio of 41.18% on the public dataset YDFID-1. The experimental results show that the proposed method can better detect and locate the defects of color-patterned fabrics compared with several other state-of-the-art unsupervised fabric defect detection methods.

Improving lightweight model for fabric defect segmentation via contrastive knowledge distillation

“…However, it is difficult to determine the appropriate pruning strategy when facing different datasets and models. Jing [6] , Zhang [7] and Wang [8] et al improve the backbone for U-Net and DeepLabV3+ by using a lightweight network represented by MobileNetV2 [9] as the backbone network for feature extraction, which effectively improves the detection speed while compressing the model size. However, the lightweight backbone implies poor feature extraction capability, which can easily lead to degradation of segmentation accuracy in semantic segmentation tasks where defects are similar to fabric patterns.…”

FocusDet: towards high-quality digital printing fabric defect detection

“…Cheng and Yu 10 proposed a DEA_RetinaNet model by embedding the channel attention mechanism module and adaptive spatial feature fusion (ASFF) module into the RetinaNet framework, which more excellently finished the steel surface defect detection task than others. Zhang et al 11 proposed an attention-based feature fusion generative adversarial network framework for unsupervised defect detection of yarn-dyed fabrics, which can fully extract shallow, high-frequency and high-level information. Liang et al 12 utilized the Faster-RCNN framework to detect more effectively and accurately defects in transmission lines.…”

“…Zhang et al. 11 proposed an attention-based feature fusion generative adversarial network framework for unsupervised defect detection of yarn-dyed fabrics, which can fully extract shallow, high-frequency and high-level information. Liang et al.…”

Pixel-level pruning deep supervision UNet++ for detecting fabric defects

“…Experiments show that this method can effectively improve the classification accuracy of defect samples even when the number of defect samples is small. Zhang et al 17 proposed an attention-gate-based U-shaped reconstruction network (AGUR-Net) and a dual-threshold segmentation post-processing method. AGUR-Net consists of an encoder, an atrous spatial pyramid pooling module and an attention gate weighted fusion residual decoder.…”

“…Zhang et al. 17 proposed an attention-gate-based U-shaped reconstruction network (AGUR-Net) and a dual-threshold segmentation post-processing method. AGUR-Net consists of an encoder, an atrous spatial pyramid pooling module and an attention gate weighted fusion residual decoder.…”