Metraipolis › archive › dc_1fea2dcc6fe6

Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detection — arXiv:2609.06785

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06785
License (as archived)
CC0-1.0
Archived
2026-10-16T15:09:23.234Z
SHA-256 of the archived text
94b2eb0195416cc277ad051e8fbf8bd05726d164f4b8c853edda713bf09eed0d
Stable URL of this page
https://metraipolis.com/documento/dc_1fea2dcc6fe6

How to cite

Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detection — arXiv:2609.06785 — arXiv (en), https://arxiv.org/abs/2609.06785 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1fea2dcc6fe6 (Metraipolis archive dc_1fea2dcc6fe6, sha256 94b2eb0195416cc277ad051e8fbf8bd05726d164f4b8c853edda713bf09eed0d)
BibTeX
@misc{dc1fea2dcc6fe6,
  title = {Unified Multi-Layer Subspace Modeling for Cross-Domain OOD Detection — arXiv:2609.06785},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06785},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1fea2dcc6fe6; sha256 94b2eb0195416cc277ad051e8fbf8bd05726d164f4b8c853edda713bf09eed0d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06785. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Out-of-Distribution (OOD) detection remains a fundamental challenge for neural networks, whose predictions can be overconfident on inputs that deviate from the training distribution. Most post-hoc OOD detection methods derive scores from a single representation level (eg., logits or penultimate features) or combine multiple layers via depth selection or OOD-calibrated weighting. However, because OOD shifts are diverse, the most informative representation level can vary strongly across OOD types and domains, making fixed-layer choices and OOD-calibrated aggregation brittle. In this paper, we propose PRISM (Projected Representation with Intermediate-layer Subspace Modeling), a model-agnostic post-hoc OOD detection method that models a unified multi-layer feature representation rather than aggregating independently scored layers. PRISM fuses intermediate and deep features into a single hierarchical embedding, estimates an in-distribution (ID) principal subspace, and then combines two complementary signals: (i) a class-conditional Mahalanobis distance in the projected subspace and (ii) the residual energy orthogonal to the learned manifold. This simple design avoids OOD-tuned layer weighting while capturing both in-subspace semantic deviations and off-subspace anomalies. Across diverse benchmarks spanning natural images, medical imaging, and industrial visual inspection, PRISM achieves consistent state-of-the-art cross-domain OOD detection performance with a single default configuration across all evaluated domains and architectures. We further show that PRISM incurs minimal inference overhead, making it practical for real-world deployment.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.06785 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T14:49:57.128Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).