Metraipolis › archive › dc_4971a95bc57b

PatchGen: Learning Soft Intra-Image Predictive Subsets for Visual Generalization — arXiv:2608.12766

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12766
License (as archived)
CC0-1.0
Archived
2026-10-19T04:55:35.811Z
SHA-256 of the archived text
92b6ab649c18ea43bc520176e1db2d95aa51f8e3989c82f3fa7006e8ec5cd155
Stable URL of this page
https://metraipolis.com/documento/dc_4971a95bc57b

How to cite

PatchGen: Learning Soft Intra-Image Predictive Subsets for Visual Generalization — arXiv:2608.12766 — arXiv (en), https://arxiv.org/abs/2608.12766 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4971a95bc57b (Metraipolis archive dc_4971a95bc57b, sha256 92b6ab649c18ea43bc520176e1db2d95aa51f8e3989c82f3fa7006e8ec5cd155)
BibTeX
@misc{dc4971a95bc57b,
  title = {PatchGen: Learning Soft Intra-Image Predictive Subsets for Visual Generalization — arXiv:2608.12766},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12766},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4971a95bc57b; sha256 92b6ab649c18ea43bc520176e1db2d95aa51f8e3989c82f3fa7006e8ec5cd155},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12766. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Visual classifiers are expected to generalize under data shifts, target shifts, and their combinations, yet most existing methods focus on domain invariance while failing to address intra-image predictive sufficiency. We investigate the structural hypothesis that each image contains a sample-adaptive oracle intra-image predictive subset sufficient for label prediction, while the remaining patches form non-essential complementary context that may correlate with the label. The theoretical analysis shows that restricting prediction to this oracle subset preserves the Bayes risk achievable by the full-patch representation while admitting a complexity bound that tightens with the oracle-subset size. Based on this view, we propose PatchGen, a text-free module that learns a sample-dependent soft predictive-subset mask as a task-driven proxy for the unobserved oracle subset mask. Specifically, histopathology visualizations suggest that PatchGen assigns higher scores to tumor-consistent regions than to some frequently co-occurring inflammatory context. Extensive experiments on natural and histopathological image benchmarks spanning all three shift settings show that PatchGen improves average performance over matched-backbone baselines in most evaluated configurations, enhances generalization to unknown classes, and remains competitive with vision-language methods without text supervision.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.12766 — 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 2026-10-19T04:46:30.061Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).