

























Abstract:Detecting out-of-distribution (OOD) data is critical for machine learning, be it for safety reasons or to enable open-ended learning. However, beyond mere detection, choosing an appropriate course of action typically hinges on the type of OOD data encountered. Unfortunately, the latter is generally not distinguished in practice, as modern OOD detection methods collapse distributional shifts into single scalar outlier scores. This work argues that scalar-based methods are thus insufficient for OOD data to be properly contextualized and prospectively exploited, a limitation we overcome with the introduction of DISC: Diffusion-based Statistical Characterization. DISC leverages the iterative denoising process of diffusion models to extract a rich, multi-dimensional feature vector that captures statistical discrepancies across multiple noise levels. Extensive experiments on image and tabular benchmarks show that DISC matches or surpasses state-of-the-art detectors for OOD detection and, crucially, also classifies OOD type, a capability largely absent from prior work. As such, our work enables a shift from simple binary OOD detection to a more granular detection.
| Comments: | Accepted at AISTATS 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2510.17381 [cs.LG] |
| (or arXiv:2510.17381v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2510.17381 arXiv-issued DOI via DataCite |
From: Achref Jaziri [view email]
[v1]
Mon, 20 Oct 2025 10:18:45 UTC (40,701 KB)
[v2]
Mon, 27 Apr 2026 11:47:08 UTC (4,854 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。