A Geometry-Based View of Mahalanobis OOD Detection

2025-10-17 · Denis Janiak, Jakub Binkowski, Tomasz Kajdanowicz arxiv

Out-of-distribution (OOD) detection is critical for reliable deployment of vision models. Mahalanobis-based detectors remain strong baselines, yet their performance varies widely across modern pretrained representations, and it is unclear which properties of a feature space cause these methods to succeed or fail. We conduct a large-scale study across diverse foundation-model backbones and Mahalanobis variants. First, we show that Mahalanobis-style OOD detection is not universally reliable: performance is highly representation-dependent and can shift substantially with pretraining data and fine-tuning regimes. Second, we link this variability to in-distribution geometry and identify a two-term ID summary that consistently tracks Mahalanobis OOD behavior across detectors: within-class spectral structure and local intrinsic dimensionality. Finally, we treat normalization as a geometric control mechanism and introduce radially scaled $\ell_2$ normalization, $φ_β(z)=z/\|z\|^β$, which preserves directions while contracting or expanding feature radii. Varying $β$ changes the radii while preserving directions, so the same quadratic detector sees a different ID geometry. We choose $β$ from ID-only geometry signals and typically outperform fixed normalization baselines.

📄 PDF Abstract BibTeX arXiv:2510.15202

Code (0)

등록된 구현이 없습니다.

Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry

2026-05-18 · Ningkang Peng, Xuanming Chen, Yanhui Gu arxiv

Long-tailed out-of-distribution (LT-OOD) detection is often addressed with specialized training, including auxiliary out-of-distribution (OOD) data, abstention heads, contrastive objectives, energy losses, or gradient-co…

Large Margin Nearest Neighbor Classification using Curved Mahalanobis Distances

2016-09-22 · Frank Nielsen, Boris Muzellec, Richard Nock

We consider the supervised classification problem of machine learning in Cayley-Klein projective geometries: We show how to learn a curved Mahalanobis metric distance corresponding to either the hyperbolic geometry or th…

BIG-bench Machine Learning Classification General Classification

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

2026-05-14 · Donghwan Kim, Hyunsoo Yoon arxiv

Out-of-distribution (OOD) detection is a critical component for ensuring the reliability of deep neural networks in safety-critical applications. In this work, we present a key empirical observation: for in-distribution …

Mahalanobis PatchCore: Covariance-Aware and Streaming-Compatible Industrial Anomaly Detection

2026-05-26 · Niccolò Ferrari, Oligert Osmani, Evelina Lamma arxiv

Industrial visual anomaly detection is usually one-class: normal images are abundant, while defects are rare, heterogeneous, and often unavailable during system design. PatchCore-style retrieval suits this setting becaus…

Dimensionality Reduction Anomaly Detection

Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins

2026-04-10 · Rahul D Ray arxiv

The ability to detect out-of-distribution (OOD) inputs is fundamental to safe deployment of machine learning systems. Yet, current methods often rely on feature representations that are optimised solely for classificatio…