Papers › PUAD: Frustratingly Simple Method for Robust Anomaly Detection

PUAD: Frustratingly Simple Method for Robust Anomaly Detection

23 Feb 2024arXiv:2402.15143archive 2025-07-28

Shota Sugawara, Ryuji Imamura

Developing an accurate and fast anomaly detection model is an important task in real-time computer vision applications. There has been much research to develop a single model that detects either structural or logical anomalies, which are inherently distinct. The majority of the existing approaches implicitly assume that the anomaly can be represented by identifying the anomalous location. However, we argue that logical anomalies, such as the wrong number of objects, can not be well-represented by the spatial feature maps and require an alternative approach. In addition, we focused on the possibility of detecting logical anomalies by using an out-of-distribution detection approach on the feature space, which aggregates the spatial information of the feature map. As a demonstration, we propose a method that incorporates a simple out-of-distribution detection method on the feature space against state-of-the-art reconstruction-based approaches. Despite the simplicity of our proposal, our method PUAD (Picturable and Unpicturable Anomaly Detection) achieves state-of-the-art performance on the MVTec LOCO AD dataset.

PaperPDFConference PDFCode

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

Code

LeapMind/PUAD officialmentioned in papermentioned on GitHubpytorchApache-2.0 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 DetectionOut-of-Distribution Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection MVTec LOCO AD PUAD-M Avg. Detection AUROC 94.4 #3 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD PUAD-M Detection AUROC (only logical) 93.7 #3 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD PUAD-M Detection AUROC (only structural) 95.9 #3 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD PUAD-S Avg. Detection AUROC 93.1 #5 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD PUAD-S Detection AUROC (only logical) 92.0 #5 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD PUAD-S Detection AUROC (only structural) 94.1 #5 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.

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