Attention-based Feature Fusion Generative Adversarial Network for yarn-dyed fabric defect detection

Abstract

Defects on the surface of yarn-dyed fabrics are one of the important factors affecting the quality of fabrics. Defect detection is the core link of quality control. Due to the diversity of yarn-dyed fabric patterns and the scarcity of defect samples, reconstruction-based unsupervised deep learning algorithms have received extensive attention in the field of fabric defect detection. However, most existing deep learning algorithms cannot fully extract shallow, high-frequency and high-level information, which limits their ability to reconstruct yarn-dyed fabric images. In this article, we propose an Attention-based Feature Fusion Generative Adversarial Network framework for unsupervised defect detection of yarn-dyed fabrics. The framework utilizes a modified Feature Pyramid Network to fuse multi-level information and utilizes an attention mechanism to enhance the model's feature representation capabilities. The Attention-based Feature Fusion Generative Adversarial Network consists of an attention fusion generator and a patch-level discriminator. In the attention fusion generator, the Feature Pyramid Network with EfficientNetV2 as the backbone is used as the core building block, and different feature fusion methods are used to avoid the loss of information in the process of network deepening. The attention mechanism is used to enhance the channel and spatial-wise correlation of features, which helps the model to focus on more meaningful information by recalibrating the feature maps. In the discriminator, the patch-level discriminator is used to calculate the similarity between the reconstructed image and the original image from a local perspective, thereby improving the model's attention to texture details. Experimental results on public datasets demonstrate the effectiveness of the proposed method compared to other methods.

Supervised Attention-Based Bidirectional Long Short-Term Memory Network for Nonlinear Dynamic Soft Sensor Application

“…The above method is the attention mechanism, the essence of which focus limited attention on the focused information, i.e., to calculate the similarity between the input and the target. 35 To summarize, the attention function is to calculate the similarity between a query vector and a set of keys in a key-value pair and normalize the correlation to get the weights of the values corresponding to the keys, and then weight the values to obtain the final result. 36 The similarity between the input and output is compared using a mapping s to represent it.…”

“…To solve a similar problem, the similarity between the intermediate results of the input and the target information is calculated in the encoding stage, and the results are subsequently passed to the decoder to obtain the output sequence so that a better understanding of which state information is more critical to the output sequence can be obtained. The above method is the attention mechanism, the essence of which focus limited attention on the focused information, i.e., to calculate the similarity between the input and the target . To summarize, the attention function is to calculate the similarity between a query vector and a set of keys in a key-value pair and normalize the correlation to get the weights of the values corresponding to the keys, and then weight the values to obtain the final result…”

QA-USTNet: Yarn-dyed fabric defect detection via U-shaped Swin Transformer Network based on Quadtree Attention

“…The unsupervised fabric defect detection methods have attracted the attention of some researchers because they do not need a large number of defect samples and manual labeling. 17,20,21 Zhang et al. 36 employed a denoising convolution auto-encoder (DCAE) model, which completed image reconstruction by superimposing Gaussian noise on the image and inputting it into the encoder and decoder, and initially realized the detection and localization of defective areas for yarn-dyed shirt piece.…”

“…In the unsupervised learning method of fabric defect detection, there are classical unsupervised learning models, such as auto-encoder (AE), [16][17][18] variational auto-encoder (VAE), 19 generative adversarial network (GAN), [20][21][22][23] etc. These unsupervised models mainly rely on convolutional neural networks (CNNs) to extract features, but these still have limitations.…”

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

“…Among defect detection methods based on unsupervised deep learning, feature representation-based methods detect and localize defects through feature matching, feature distance measurement, or feature reconstruction. [11][12][13] Generation-based methods detect and localize defects by comparing reconstructed images with input images, including autoencoders, [14][15][16] variational autoencoders, 17 generative adversarial networks, [18][19][20][21] etc. However, current methods still have some limitations.…”