Transformer architecture based on mutual attention for image-anomaly detection

Image-anomaly detection, which is widely used in industrial fields. Previous studies that attempted to address this problem often trained convolutional neural network-based models (e.g., autoencoders and generative adversarial networks) to reconstruct covered parts of input images and calculate the difference between the input and reconstructed images. However, convolutional operations are effective at extracting local features, making it difficult to identify larger image anomalies. To this end, we propose a transformer architecture based on mutual attention for image-anomaly separation. This architecture can capture long-term dependencies and fuse local and global features to facilitate better image-anomaly detection. Our method was extensively evaluated on several benchmarks, and experimental results showed that it improved the detection capability by 3.1% and localization capability by 1.0% compared with state-of-the-art reconstruction-based methods.