← Back to all news
arXiv AI By Wonseok Shin, Songkuk Kim

Don't Replace, Complement: A Detector-Agnostic Subspace Signal for Near-OOD Detection

Read the original on arXiv AI →

The paper introduces PLUS, a detector‑agnostic subspace signal that enhances near‑out‑of‑distribution (near‑OOD) detection. PLUS selects the most class‑active neurons via a sparse autoencoder, orthonormalizes their decoder directions to form a low‑dimensional subspace, and scores inputs using a per‑class whitened squared Mahalanobis distance within that subspace. The resulting signal is fused additively with any calibrated base score using a single global weight, improving near‑OOD AUROC across 126 detector–backbone combinations while largely preserving far‑OOD performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
6d ago

MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse

MahaVar is a post‑hoc out‑of‑distribution detector that augments the Mahalanobis distance with a class‑wise distance variance term. The authors observe that in‑distribution samples exhibit a sharp minimum in class‑wise Mahalanobis distances, leading to high variance across classes, whereas OOD samples show a flatter structure and lower variance. Theoretical analysis based on Neural Collapse supports this observation, and empirical results on CIFAR‑100 and ImageNet demonstrate state‑of‑the‑art performance compared to existing Mahalanobis‑based methods.

By Donghwan Kim, Hyunsoo Yoon
benchmarkssafety
More like this →
arXiv Computer Vision
Oct 2

Dataset Identity, Not Novelty: The Source of an Inflated OOD Detection Gain

The paper investigates why post‑hoc out‑of‑distribution (OOD) detectors often report inflated gains. It shows that many detectors learn to recognize the specific dataset they were trained on rather than true novelty, a phenomenon called the inflation gap. By holding out entire OOD datasets during evaluation, the authors demonstrate that most reported gains vanish, and they provide a closed‑form method to predict which fits will inflate.

By Donghoon Lee, Shinjin Kang
benchmarks
More like this →