Anomaly Detection on Anomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102

Metric: ROC-AUC (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide augmentations

Sort:

#	Model↕	ROC-AUC▼	Augmentations	Paper	Date↕	Code
1	PsudoLabels CLIP ViT	98.3	Yes	Out-of-Distribution Detection Without Class Labels	2021-12-14	-
2	CSI	94.7	No	CSI: Novelty Detection via Contrastive Learning ...	2020-07-16	Code
3	DN2 CLIP ViT	93.2	Yes	Deep Nearest Neighbor Anomaly Detection	2020-02-24	-
4	GOAD	92.8	No	Classification-Based Anomaly Detection for Gener...	2020-05-05	Code
5	ROT+Trans	86.3	No	Using Self-Supervised Learning Can Improve Model...	2019-06-28	Code

#1PsudoLabels CLIP ViTSOTA
98.3
ROC-AUC· Augmentations· 2021-12-14
Out-of-Distribution Detection Without Class Labels
#2CSISOTA
94.7
ROC-AUC· 2020-07-16
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances Code
#3DN2 CLIP ViTSOTA
93.2
ROC-AUC· Augmentations· 2020-02-24
Deep Nearest Neighbor Anomaly Detection
#4GOAD
92.8
ROC-AUC· 2020-05-05
Classification-Based Anomaly Detection for General Data Code
#5ROT+TransSOTA
86.3
ROC-AUC· 2019-06-28
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty Code