Anomaly Detection on Unlabeled CIFAR-10 vs CIFAR-100

Metric: AUROC (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide augmentations

#	Model↕	AUROC▼	Augmentations	Paper	Date↕	Code
1	PsudoLabels ViT	96.7	Yes	Out-of-Distribution Detection Without Class Labels	2021-12-14	-
2	PsudoLabels ResNet-152	93.3	Yes	Out-of-Distribution Detection Without Class Labels	2021-12-14	-
3	PsudoLabels ResNet-18	90.8	Yes	Out-of-Distribution Detection Without Class Labels	2021-12-14	-
4	SCAN Features	90.2	No	Out-of-Distribution Detection Without Class Labels	2021-12-14	-
5	MeanShifted	90	Yes	Mean-Shifted Contrastive Loss for Anomaly Detect...	2021-06-07	Code
6	SSD	89.6	No	SSD: A Unified Framework for Self-Supervised Out...	2021-03-22	Code
7	CSI	89.3	No	CSI: Novelty Detection via Contrastive Learning ...	2020-07-16	Code
8	GOAD	89.2	No	Classification-Based Anomaly Detection for Gener...	2020-05-05	Code
9	MTL	82.92	No	Shifting Transformation Learning for Out-of-Dist...	2021-06-07	-
10	Input Complexity (Glow)	73.6	No	Input complexity and out-of-distribution detecti...	2019-09-25	Code
11	Likelihood (Glow)	58.2	No	Input complexity and out-of-distribution detecti...	2019-09-25	Code
12	Input Complexity (PixelCNN++)	53.5	No	Input complexity and out-of-distribution detecti...	2019-09-25	Code
13	Likelihood (PixelCNN++)	52.6	No	Input complexity and out-of-distribution detecti...	2019-09-25	Code