← Back to all news
arXiv AI By Donghwan Kim, Hyunsoo Yoon

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

Read the original on arXiv AI →

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.

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
1d ago

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

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.

By Wonseok Shin, Songkuk Kim
More like this →
arXiv Machine Learning
Oct 19

Escaping Parameter Space: Tight Generalization Bounds via Representation Quality

The paper presents a tight generalization bound for deterministic neural networks that relies on the quality of their last hidden layer representations rather than traditional parameter-space metrics. By using a parameter‑free k‑nearest‑neighbor classifier to assess representation quality, the bound decomposes into three measurable components—local class geometry, decoder‑network agreement, and training stability—providing both a non‑vacuous certificate and a diagnostic tool for understanding generalization. Experiments show the bound achieves an 8.0‑percentage‑point gap to test error on CIFAR‑10 with ResNet‑18, yields the first non‑vacuous certificates on CIFAR‑100, and certifies 1.4 % on CIFAR‑10 and 23.1 % on 1,000‑class ImageNet using frozen DINOv2 representations.

By Niclas G\"oring, Shuofeng Zhang, Branton DeMoss, Ard A. Louis
More like this →