Contrastive Vision Transformer for Self-supervised Out-of-distribution Detection

Hengding Wang, Yuchen Lu, Xi Chen

Keywords: Out-of-distribution, self-supervised learning, contrastive learning, vision transformer

Abstract: Out-of-distribution (OOD) detection is a type of technique that aims to detect abnormal samples that don't belong to the distribution of training data (or in-distribution (ID) data). The technique has been applied to various image classification tasks to identify abnormal image samples for which the abnormality is caused by semantic shift (from different classes) or covariate shift (from different domains). However, disentangling OOD samples caused by different shifts remains a challenge in image OOD detection. This paper proposes Contrastive Vision Transformer (CVT), an attention-based contrastive learning model, for self-supervised OOD detection in image classification tasks. Specifically, vision transformer architecture is integrated as a feature extracting module under a contrastive learning framework. An empirical ensemble module is developed to extract representative ensemble features, from which a balance can be achieved between semantic and covariate OOD samples. The proposed CVT model is tested in various self-supervised OOD detection tasks, and our approach outperforms state-of-the-art methods by 5.5% AUROC on CIFAR-10 (ID) vs. CIFAR-100 (OOD), and by 10.7% AUROC on CIFAR-100 (ID) vs. CIFAR-10 (OOD).

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

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

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Unsupervised and Self-supervised learning