Papers › Visual Anomaly Detection via Dual-Attention Transformer and Discriminative Flow

Visual Anomaly Detection via Dual-Attention Transformer and Discriminative Flow

31 Mar 2023arXiv:2303.17882archive 2025-07-28

Haiming Yao, Wei Luo, Wenyong Yu

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.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

hmyao22/DADF pytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly Detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Anomaly Detection	MVTec LOCO AD	DADF	Avg. Detection AUROC	83.7	#21 of 40	Archive leaderboard	report
Anomaly Detection	MVTec LOCO AD	DADF	Detection AUROC (only logical)	79.2	#21 of 40	Archive leaderboard	report
Anomaly Detection	MVTec LOCO AD	DADF	Detection AUROC (only structural)	88.2	#21 of 40	Archive leaderboard	report
Anomaly Detection	MVTec LOCO AD	DADF	Segmentation AU-sPRO (until FPR 5%)	67.4	#21 of 40	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer Vision Transformer fail

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections