Anomaly Detection on One-class ImageNet-30

Metric: AUROC (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide augmentations

Sort:

#	Model↕	AUROC▼	Augmentations	Paper	Date↕	Code
1	BCE-Clip (OE)	99.9	Yes	Exposing Outlier Exposure: What Can Be Learned F...	2022-05-23	Code
2	CLIP (Zero Shot)	99.88	No	Exposing Outlier Exposure: What Can Be Learned F...	2022-05-23	Code
3	Binary Cross Entropy (OE)	97.7	Yes	Exposing Outlier Exposure: What Can Be Learned F...	2022-05-23	Code
4	CSI	91.6	No	CSI: Novelty Detection via Contrastive Learning ...	2020-07-16	Code
5	FCDD	91	Yes	Explainable Deep One-Class Classification	2020-07-03	Code
6	RotNet + Translation + Self-Attention + Resize	85.7	No	Using Self-Supervised Learning Can Improve Model...	2019-06-28	Code
7	RotNet + Translation + Self-Attention	84.8	Yes	Using Self-Supervised Learning Can Improve Model...	2019-06-28	Code
8	RotNet + Self-Attention	81.6	Yes	Using Self-Supervised Learning Can Improve Model...	2019-06-28	Code
9	RotNet + Translation	77.9	Yes	Using Self-Supervised Learning Can Improve Model...	2019-06-28	Code
10	RotNet	65.3	No	Using Self-Supervised Learning Can Improve Model...	2019-06-28	Code
11	Supervised (OE)	56.1	Yes	Using Self-Supervised Learning Can Improve Model...	2019-06-28	Code

#1BCE-Clip (OE)SOTA
99.9
AUROC· Augmentations· 2022-05-23
Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images Code
#2CLIP (Zero Shot)
99.88
AUROC· 2022-05-23
Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images Code
#3Binary Cross Entropy (OE)
97.7
AUROC· Augmentations· 2022-05-23
Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images Code
#4CSISOTA
91.6
AUROC· 2020-07-16
CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances Code
#5FCDDSOTA
91
AUROC· Augmentations· 2020-07-03
Explainable Deep One-Class Classification Code
#6RotNet + Translation + Self-Attention + ResizeSOTA
85.7
AUROC· 2019-06-28
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty Code
#7RotNet + Translation + Self-Attention
84.8
AUROC· Augmentations· 2019-06-28
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty Code
#8RotNet + Self-Attention
81.6
AUROC· Augmentations· 2019-06-28
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty Code
#9RotNet + Translation
77.9
AUROC· Augmentations· 2019-06-28
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty Code
#10RotNet
65.3
AUROC· 2019-06-28
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty Code
#11Supervised (OE)
56.1
AUROC· Augmentations· 2019-06-28
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty Code