Learning and Evaluating Representations for Deep One-Class ClassificationDownload PDF

Sep 28, 2020 (edited Mar 17, 2021)ICLR 2021 PosterReaders: Everyone
  • Keywords: deep one-class classification, self-supervised learning
  • Abstract: 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.
  • One-sentence Summary: We present a two-stage framework for deep one-class classification, composed of state-of-the-art self-supervised representation learning followed by generative or discriminative one-class classifiers.
  • Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
16 Replies

Loading