Papers › Learning and Evaluating Representations for Deep One-class Classification

Learning and Evaluating Representations for Deep One-class Classification

4 Nov 2020ICLR 2021 1arXiv:2011.02578archive 2025-07-28

Kihyuk Sohn, Chun-Liang Li, Jinsung Yoon, Minho Jin, Tomas Pfister

We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. The framework not only allows to learn better representations, but also permits building one-class classifiers that are faithful to the target task. We argue that classifiers inspired by the statistical perspective in generative or discriminative models are more effective than existing approaches, such as a normality score from a surrogate classifier. We thoroughly evaluate different self-supervised representation learning algorithms under the proposed framework for one-class classification. Moreover, we present a novel distribution-augmented contrastive learning that extends training distributions via data augmentation to obstruct the uniformity of contrastive representations. In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks, including novelty and anomaly detection. Finally, we present visual explanations, confirming that the decision-making process of deep one-class classifiers is intuitive to humans. The code is available at https://github.com/google-research/deep_representation_one_class.

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

google-research/deep_representation_one_class officialmentioned in papertf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Anomaly Detection Classification Contrastive Learning Data Augmentation Decision Making General Classification One-Class Classification One-class classifier Representation Learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Anomaly Detection	MVTec AD	DisAug CLR	Detection AUROC	86.5	#118 of 148	Archive leaderboard	report
Anomaly Detection	MVTec AD	DisAug CLR	Segmentation AUROC	90.4	#118 of 148	Archive leaderboard	report
Anomaly Detection	MVTec AD	RotNet (MLP Head)	Detection AUROC	86.3	#119 of 148	Archive leaderboard	report
Anomaly Detection	MVTec AD	RotNet (MLP Head)	Segmentation AUROC	93	#119 of 148	Archive leaderboard	report
Anomaly Detection	One-class CIFAR-10	DisAug CLR	AUROC	92.5	#15 of 36	Archive leaderboard	report
Anomaly Detection	One-class CIFAR-100	DisAug CLR	AUROC	86.5	#8 of 15	Archive leaderboard	report
Anomaly Detection	One-class CIFAR-100	Rotation Prediction	AUROC	84.1	#10 of 15	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.

Methods

Contrastive Learning

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