Pseudo-label Induced Subspace Representation Learning for Robust Out-of-Distribution Detection

TL;DR

This paper introduces a new OOD detection method using pseudo-label-induced subspace representations, which relaxes previous assumptions and improves separation between in-distribution and out-of-distribution samples.

Contribution

It proposes a novel framework combining pseudo-labels with subspace learning and a combined loss function to enhance OOD detection robustness under relaxed assumptions.

Findings

Effective in distinguishing ID and OOD samples

Outperforms existing feature-based OOD detection methods

Validated through extensive experiments

Abstract

Out-of-distribution (OOD) detection lies at the heart of robust artificial intelligence (AI), aiming to identify samples from novel distributions beyond the training set. Recent approaches have exploited feature representations as distinguishing signatures for OOD detection. However, most existing methods rely on restrictive assumptions on the feature space that limit the separability between in-distribution (ID) and OOD samples. In this work, we propose a novel OOD detection framework based on a pseudo-label-induced subspace representation, that works under more relaxed and natural assumptions compared to existing feature-based techniques. In addition, we introduce a simple yet effective learning criterion that integrates a cross-entropy-based ID classification loss with a subspace distance-based regularization loss to enhance ID-OOD separability. Extensive experiments validate the effectiveness of our framework.