Dual-Attention Transformer and Discriminative Flow for Industrial Visual Anomaly Detection

In this paper, we introduce the novel state-of-the-art Dual-attention Transformer and Discriminative Flow (DADF) framework for visual anomaly detection. Based on only normal knowledge, visual anomaly detection has wide applications in industrial scenarios and has attracted significant attention. However, most existing methods fail to meet the requirements of logic defect detection under complex semantic conditions. In contrast, the proposed DADF presents a new paradigm: it firstly leverages a pre-trained network to acquire multi-scale prior embeddings, followed by the development of a vision Transformer with dual attention mechanisms, namely self-attention and memorial-attention, to achieve global-local two-level reconstruction for prior embeddings with the sequential and normality association. Additionally, we propose using normalizing flow to establish discriminative likelihood for the joint distribution of prior and reconstructions at each scale. The experimental results validate the effectiveness of the proposed DADF approach, as evidenced by the impressive performance metrics obtained across various benchmarks, especially for logic defects with complex semantics. Specifically, DADF achieves image-level and pixel-level AUROC scores of 98.3 and 98.4, respectively, on the Mvtec AD benchmark, and an image-level AUROC score of 83.7 and a pixel sPRO score of 67.4 on the Mvtec LOCO AD benchmark. Additionally, we applied DADF to a real-world Printed Circuit Board (PCB) industrial defect inspection task, further demonstrating its efficacy in practical scenarios. The source code of DADF is available at https://github.com/hmyao22/DADF. Note to Practitioners-Most of the current industrial visual inspection techniques can only detect structural defects under uncomplicated semantic settings. Detecting anomalies in products featuring intricate components and logical defects with high-level semantics remains a considerable challenge. The presented DADF is a robust model that can effectively identify defects in products with complex components, such as Printed Circuit Boards (PCBs). Furthermore, it can also accurately detect both structural and logical defects, which is of significant importance for practical industrial applications.