When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations
Deep neural networks have achieved remarkable performance across medical imaging tasks, yet their tendency to overgeneralize under distributional shifts poses a major obstacle to safe clinical deployment. Out-of-Distribution (OOD) detection methods aim to mitigate this risk, but most existing approaches rely on opaque internal signals with poorly understood semantic meaning, limiting trust in safety-critical settings. In this work, we propose an interpretable OOD detection framework that probes the stability of model predictions under class-conditioned semantic perturbations. Leveraging sparse autoencoders (SAEs), we learn class-specific concept vectors from in-distribution data that dise...
| Authors | Anju Chhetri, Pratik Shrestha, Ramesh Rana et al. |
|---|---|
| Primary category | cs.LG |
| Published | 15 June 2026 |
| Last updated at source | 21 June 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.