Papers › Locally varying distance transform for unsupervised visual anomaly detection

Locally varying distance transform for unsupervised visual anomaly detection

23 Oct 2022ECCV 2022 10archive 2025-07-28

Wen-Yan Lin, Zhonghang Liu, Siying Liu

Unsupervised anomaly detection on image data is notoriously unstable. We believe this is because many classical anomaly detectors implicitly assume data is low dimensional. However, image data is always high dimensional. Images can be projected to a low dimensional embedding but such projections rely on global transformations that truncate minor variations. As anomalies are rare, the final embedding often lacks the key variations needed to distinguish anomalies from normal instances. This paper proposes a new embedding using a set of locally varying data projections, with each projection responsible for persevering the variations that distinguish a local cluster of instances from all other instances. The locally varying embedding ensures the variations that distinguish anomalies are preserved, while simultaneously allowing the probability that an instance belongs to a cluster, to be statistically inferred from the one-dimensional, local projection associated with the cluster. Statistical agglomeration of an instance’s cluster membership probabilities, creates a global measure of its affinity to the dataset and causes anomalies to emerge, as instances whose affinity scores are surprisingly low.

PaperPDFCode

Code

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

Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomalyUnsupervised Anomaly Detection with Specified Settings -- 1% anomalyUnsupervised Anomaly Detection with Specified Settings -- 10% anomalyUnsupervised Anomaly Detection with Specified Settings -- 20% anomalyUnsupervised Anomaly Detection with Specified Settings -- 30% anomaly

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Anomaly Detection MNIST LVAD AUROC 0.937 #1 of 1 Archive leaderboard report
Unsupervised Anomaly Detection STL-10 LVAD AUC-ROC 0.996 #1 of 1 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly CIFAR-10 LVAD AUC-ROC 0.930 #1 of 6 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly Cats and Dogs LVAD AUC-ROC 0.981 #2 of 6 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly Fashion-MNIST LVAD AUC-ROC 0.896 #3 of 5 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly MNIST LVAD AUC-ROC 0.974 #1 of 5 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly STL-10 LVAD AUC-ROC 0.998 #1 of 6 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly CIFAR-10 LVAD AUC-ROC 0.940 #1 of 6 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly Cats and Dogs LVAD AUC-ROC 0.978 #2 of 5 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly Fashion-MNIST LVAD AUC-ROC 0.909 #2 of 5 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly MNIST LVAD AUC-ROC 0.948 #1 of 5 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly STL-10 LVAD AUC-ROC 0.993 #1 of 6 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly CIFAR-10 LVAD AUC-ROC 0.903 #1 of 6 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly Cats and Dogs LVAD AUC-ROC 0.927 #4 of 6 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly Fashion-MNIST LVAD AUC-ROC 0.899 #2 of 5 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly MNIST LVAD AUC-ROC 0.938 #1 of 5 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly STL-10 LVAD AUC-ROC 0.979 #2 of 6 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly Cats and Dogs LVAD AUC-ROC 0.851 #4 of 6 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly Fashion-MNIST LVAD AUC-ROC 0.884 #2 of 5 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly MNIST LVAD AUC-ROC 0.923 #1 of 5 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly STL-10 LVAD AUC-ROC 0.983 #2 of 6 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly cifar10 LVAD AUC-ROC 0.854 #3 of 6 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly ASSIRA Cat Vs Dog LVAD AUC-ROC 0.780 #3 of 6 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly CIFAR-10 LVAD AUC-ROC 0.816 #3 of 6 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly Fashion-MNIST LVAD AUC-ROC 0.868 #2 of 5 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly MNIST LVAD AUC-ROC 0.904 #1 of 5 Archive leaderboard report
Unsupervised Anomaly Detection with Specified Settings -- 30% anomaly STL-10 LVAD AUC-ROC 0.977 #2 of 6 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