Metraipolis › archive › dc_e707cd49e5cf

PWLR: Pairwise Witness Local Rejection for Boundary-Aware Out-of-Distribution Detection — arXiv:2608.15802

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.15802
License (as archived): CC0-1.0
Archived: 2026-10-18T19:44:13.873Z
SHA-256 of the archived text: dacb887a58dd4bdfcf6b7d7c80955a2bee3c3efc4e7daeebd3ae6f7c8f7db212
Stable URL of this page: https://metraipolis.com/documento/dc_e707cd49e5cf

How to cite

PWLR: Pairwise Witness Local Rejection for Boundary-Aware Out-of-Distribution Detection — arXiv:2608.15802 — arXiv (en), https://arxiv.org/abs/2608.15802 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e707cd49e5cf (Metraipolis archive dc_e707cd49e5cf, sha256 dacb887a58dd4bdfcf6b7d7c80955a2bee3c3efc4e7daeebd3ae6f7c8f7db212)

BibTeX

@misc{dce707cd49e5cf,
  title = {PWLR: Pairwise Witness Local Rejection for Boundary-Aware Out-of-Distribution Detection — arXiv:2608.15802},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15802},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e707cd49e5cf; sha256 dacb887a58dd4bdfcf6b7d7c80955a2bee3c3efc4e7daeebd3ae6f7c8f7db212},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15802. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Out-of-distribution (OOD) detection remains challenging for image classifiers, especially when near-OOD samples lie close to in-distribution (ID) class boundaries. Recent vision-language detectors improve OOD detection through class semantics, local prompting, or LLM-generated outlier concepts, but seldom use language as explicit boundary evidence between confusing ID classes. We propose Pairwise Witness Local Rejection (PWLR), which uses an MLLM offline to describe visible local cues that favor one ID class over a specific rival class. These cue phrases are then screened with ID-only data under a frozen vision-language backbone, so that only reliable local verifiers are kept. At inference, PWLR first retains a small set of globally plausible classes, then checks whether any of them is locally supported against its most relevant rivals, and finally combines this pairwise local evidence with the global class score through calibration. Experiments on ImageNet-100 far-OOD, cleaner/challenging OOD and near-OOD benchmarks show that PWLR consistently improves strong vision-language baselines across multiple backbones. Source code will be released.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.15802 — 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 2026-10-18T19:02:44.280Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).