TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Anomaly Detection	Anomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102	PsudoLabels CLIP ViT	ROC-AUC	98.3	# 1
Anomaly Detection	Anomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102	PsudoLabels CLIP ViT	Network	ViT	# 1
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	SCAN Features	ROC-AUC	90.2	# 7
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	SCAN Features	Network	ResNet-18	# 1
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	PsudoLabels ResNet-18	ROC-AUC	94.3	# 4
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	PsudoLabels ResNet-18	Network	ResNet-18	# 1
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	PsudoLabels ResNet-152	ROC-AUC	95.7	# 3
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	PsudoLabels ResNet-152	Network	ResNet-152	# 1
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	PsudoLabels ViT	ROC-AUC	99.1	# 1
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	PsudoLabels ViT	Network	ViT	# 1
Anomaly Detection	Anomaly Detection on Unlabeled ImageNet-30 vs CUB-200	PsudoLabels CLIP ViT	ROC-AUC	99.4	# 1
Anomaly Detection	Anomaly Detection on Unlabeled ImageNet-30 vs CUB-200	PsudoLabels CLIP ViT	Network	ViT	# 1
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	PsudoLabels ResNet-152	AUROC	93.3	# 2
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	PsudoLabels ResNet-152	Network	ResNet-152	# 1
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	PsudoLabels ResNet-18	AUROC	90.8	# 3
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	PsudoLabels ResNet-18	Network	ResNet-18	# 1
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	PsudoLabels ViT	AUROC	96.7	# 1
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	PsudoLabels ViT	Network	ViT	# 1
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	SCAN Features	AUROC	90.2	# 4
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	SCAN Features	Network	ResNet-18	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/out-of-distribution-detection-without-class/anomaly-detection-on-anomaly-detection-on-2)](https://paperswithcode.com/sota/anomaly-detection-on-anomaly-detection-on-2?p=out-of-distribution-detection-without-class)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/out-of-distribution-detection-without-class/anomaly-detection-on-anomaly-detection-on)](https://paperswithcode.com/sota/anomaly-detection-on-anomaly-detection-on?p=out-of-distribution-detection-without-class)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/out-of-distribution-detection-without-class/anomaly-detection-on-anomaly-detection-on-1)](https://paperswithcode.com/sota/anomaly-detection-on-anomaly-detection-on-1?p=out-of-distribution-detection-without-class)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/out-of-distribution-detection-without-class/anomaly-detection-on-unlabeled-cifar-10-vs)](https://paperswithcode.com/sota/anomaly-detection-on-unlabeled-cifar-10-vs?p=out-of-distribution-detection-without-class)`

Out-of-Distribution Detection Without Class Labels

14 Dec 2021 · 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.

PDF Abstract

Code

Add Remove Mark official

No code implementations yet. Submit your code now

Tasks

Add Remove

Anomaly Detection

Clustering

Image Clustering

Novelty Detection

Out-of-Distribution Detection

Physical Video Anomaly Detection

Datasets

CIFAR-10

CIFAR-100

SVHN

Oxford 102 Flower

LSUN

Places205

Results from the Paper

Edit

Ranked #1 on Anomaly Detection on Anomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102 (using extra training data)

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Anomaly Detection	Anomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102	PsudoLabels CLIP ViT	ROC-AUC	98.3	# 1	Compare
Anomaly Detection		PsudoLabels CLIP ViT	Network	ViT	# 1	Compare
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	SCAN Features	ROC-AUC	90.2	# 7	Compare
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	SCAN Features	Network	ResNet-18	# 1	Compare
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	PsudoLabels ResNet-18	ROC-AUC	94.3	# 4	Compare
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	PsudoLabels ResNet-18	Network	ResNet-18	# 1	Compare
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	PsudoLabels ResNet-152	ROC-AUC	95.7	# 3	Compare
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	PsudoLabels ResNet-152	Network	ResNet-152	# 1	Compare
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	PsudoLabels ViT	ROC-AUC	99.1	# 1	Compare
Anomaly Detection	Anomaly Detection on Unlabeled CIFAR-10 vs LSUN (Fix)	PsudoLabels ViT	Network	ViT	# 1	Compare
Anomaly Detection	Anomaly Detection on Unlabeled ImageNet-30 vs CUB-200	PsudoLabels CLIP ViT	ROC-AUC	99.4	# 1	Compare
Anomaly Detection	Anomaly Detection on Unlabeled ImageNet-30 vs CUB-200	PsudoLabels CLIP ViT	Network	ViT	# 1	Compare
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	PsudoLabels ResNet-152	AUROC	93.3	# 2	Compare
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	PsudoLabels ResNet-152	Network	ResNet-152	# 1	Compare
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	PsudoLabels ResNet-18	AUROC	90.8	# 3	Compare
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	PsudoLabels ResNet-18	Network	ResNet-18	# 1	Compare
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	PsudoLabels ViT	AUROC	96.7	# 1	Compare
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	PsudoLabels ViT	Network	ViT	# 1	Compare
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	SCAN Features	AUROC	90.2	# 4	Compare
Anomaly Detection	Unlabeled CIFAR-10 vs CIFAR-100	SCAN Features	Network	ResNet-18	# 1	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

Out-of-Distribution Detection Without Class Labels

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove