Papers › Learning Memory-guided Normality for Anomaly Detection

Learning Memory-guided Normality for Anomaly Detection

30 Mar 2020CVPR 2020 6arXiv:2003.13228archive 2025-07-28

Hyunjong Park, Jongyoun Noh, Bumsub Ham

We address the problem of anomaly detection, that is, detecting anomalous events in a video sequence. Anomaly detection methods based on convolutional neural networks (CNNs) typically leverage proxy tasks, such as reconstructing input video frames, to learn models describing normality without seeing anomalous samples at training time, and quantify the extent of abnormalities using the reconstruction error at test time. The main drawbacks of these approaches are that they do not consider the diversity of normal patterns explicitly, and the powerful representation capacity of CNNs allows to reconstruct abnormal video frames. To address this problem, we present an unsupervised learning approach to anomaly detection that considers the diversity of normal patterns explicitly, while lessening the representation capacity of CNNs. To this end, we propose to use a memory module with a new update scheme where items in the memory record prototypical patterns of normal data. We also present novel feature compactness and separateness losses to train the memory, boosting the discriminative power of both memory items and deeply learned features from normal data. Experimental results on standard benchmarks demonstrate the effectiveness and efficiency of our approach, which outperforms the state of the art.

PaperPDFConference PDFCode

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

Code

cvlab-yonsei/MNAD officialpytorch 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 DetectionAnomaly Detection In Surveillance VideosDiversityGeneral Action Video Anomaly DetectionPhysical Video Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection MVTec LOCO AD MNAD Avg. Detection AUROC 65.1 #35 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD MNAD Detection AUROC (only logical) 60.0 #35 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD MNAD Detection AUROC (only structural) 70.2 #35 of 40 Archive leaderboard report
Anomaly Detection MVTec LOCO AD MNAD Segmentation AU-sPRO (until FPR 5%) 33.9 #35 of 40 Archive leaderboard report
General Action Video Anomaly Detection Something-Something V2 MNAD Avg. ROC-AUC 0.52 #2 of 3 Archive leaderboard report
Physical Video Anomaly Detection PHANTOM MNAD Avg. ROC-AUC 0.55 #3 of 3 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