SOURCE-LINKED INTELLIGENCE

Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detection

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Out-of-Distribution (OOD) detection remains a fundamental challenge for neural networks, whose predictions can be overconfident on inputs that deviate from the training distribution. Most post-hoc OOD detection methods derive scores from a single representation level (eg., logits or penultimate features) or combine multiple layers via depth selection or OOD-calibrated weighting. However, because OOD shifts are diverse, the most informative representation level can vary strongly across OOD types and domains, making fixed-layer choices and OOD-calibrated aggregation brittle. In this paper, we pr

Read original source ↗ Open in workspace

recordType

paper

region

Global