Papers › Out-of-Distribution Detection Without Class Labels

Out-of-Distribution Detection Without Class Labels

14 Dec 2021arXiv:2112.07662archive 2025-07-28

Niv Cohen, Ron Abutbul, Yedid Hoshen

Out-of-distribution detection seeks to identify novelties, samples that deviate from the norm. The task has been found to be quite challenging, particularly in the case where the normal data distribution consists of multiple semantic classes (e.g., multiple object categories). To overcome this challenge, current approaches require manual labeling of the normal images provided during training. In this work, we tackle multi-class novelty detection without class labels. Our simple but effective solution consists of two stages: we first discover "pseudo-class" labels using unsupervised clustering. Then using these pseudo-class labels, we are able to use standard supervised out-of-distribution detection methods. We verify the performance of our method by a favorable comparison to the state-of-the-art, and provide extensive analysis and ablations.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Anomaly DetectionClusteringImage ClusteringNovelty DetectionOut-of-Distribution DetectionPhysical Video Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection Anomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102 PsudoLabels CLIP ViT Network ViT #1 of 5 Archive leaderboard report
Anomaly Detection Anomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102 PsudoLabels CLIP ViT ROC-AUC 98.3 #1 of 5 Archive leaderboard report
Anomaly Detection Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix) PsudoLabels ViT Network ViT #1 of 8 Archive leaderboard report
Anomaly Detection Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix) PsudoLabels ViT ROC-AUC 99.1 #1 of 8 Archive leaderboard report
Anomaly Detection Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix) PsudoLabels ResNet-152 Network ResNet-152 #3 of 8 Archive leaderboard report
Anomaly Detection Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix) PsudoLabels ResNet-152 ROC-AUC 95.7 #3 of 8 Archive leaderboard report
Anomaly Detection Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix) PsudoLabels ResNet-18 Network ResNet-18 #4 of 8 Archive leaderboard report
Anomaly Detection Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix) PsudoLabels ResNet-18 ROC-AUC 94.3 #4 of 8 Archive leaderboard report
Anomaly Detection Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix) SCAN Features Network ResNet-18 #7 of 8 Archive leaderboard report
Anomaly Detection Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix) SCAN Features ROC-AUC 90.2 #7 of 8 Archive leaderboard report
Anomaly Detection Anomaly Detection on Unlabeled ImageNet-30 vs CUB-200 PsudoLabels CLIP ViT Network ViT #1 of 5 Archive leaderboard report
Anomaly Detection Anomaly Detection on Unlabeled ImageNet-30 vs CUB-200 PsudoLabels CLIP ViT ROC-AUC 99.4 #1 of 5 Archive leaderboard report
Anomaly Detection Unlabeled CIFAR-10 vs CIFAR-100 PsudoLabels ViT AUROC 96.7 #1 of 13 Archive leaderboard report
Anomaly Detection Unlabeled CIFAR-10 vs CIFAR-100 PsudoLabels ViT Network ViT #1 of 13 Archive leaderboard report
Anomaly Detection Unlabeled CIFAR-10 vs CIFAR-100 PsudoLabels ResNet-152 AUROC 93.3 #2 of 13 Archive leaderboard report
Anomaly Detection Unlabeled CIFAR-10 vs CIFAR-100 PsudoLabels ResNet-152 Network ResNet-152 #2 of 13 Archive leaderboard report
Anomaly Detection Unlabeled CIFAR-10 vs CIFAR-100 PsudoLabels ResNet-18 AUROC 90.8 #3 of 13 Archive leaderboard report
Anomaly Detection Unlabeled CIFAR-10 vs CIFAR-100 PsudoLabels ResNet-18 Network ResNet-18 #3 of 13 Archive leaderboard report
Anomaly Detection Unlabeled CIFAR-10 vs CIFAR-100 SCAN Features AUROC 90.2 #4 of 13 Archive leaderboard report
Anomaly Detection Unlabeled CIFAR-10 vs CIFAR-100 SCAN Features Network ResNet-18 #4 of 13 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