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. In contrast, the proposed DTDF 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 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 DADF achieves 98.3/98.4 of image/pixel AUROC on Mvtec AD; 83.7 of image AUROC and 67.4 of pixel sPRO on Mvtec LOCO AD benchmarks, demonstrating the effectiveness of our proposed approach.

翻译：本文提出了一种新颖且达到最优性能的双注意力Transformer与判别流（DADF）框架，用于视觉异常检测。由于仅需依赖正常样本知识，视觉异常检测在工业场景中具有广泛应用并受到广泛关注。然而，现有方法大多难以满足实际需求。相比之下，本文提出的DTDF框架开创了一种新范式：首先利用预训练网络获取多尺度先验嵌入，进而构建具有双注意力机制（即自注意力和记忆注意力）的视觉Transformer，通过序列关联与正常性关联实现对先验嵌入的两级重建。此外，我们提出利用归一化流（Normalizing Flow）为每个尺度的先验与重建联合分布建立判别似然。在Mvtec AD基准上，DADF方法取得了图像级/像素级AUROC分别为98.3/98.4的性能；在Mvtec LOCO AD基准上，其图像级AUROC达83.7，像素级sPRO达67.4，充分验证了所提方法的有效性。