Pseudo-label Induced Subspace Representation Learning for Robust Out-of-Distribution Detection
This addresses robust AI by enhancing OOD detection, but appears incremental as it builds on existing feature-based methods.
The paper tackled the problem of out-of-distribution (OOD) detection by proposing a framework based on pseudo-label-induced subspace representation to improve separability between in-distribution and OOD samples under relaxed assumptions, achieving validated effectiveness in experiments.
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.