Metraipolis › archive › dc_e03b3da3bf53
Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation — arXiv:2610.00678
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00678
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:39:13.635Z
- SHA-256 of the archived text
b34519e62d0340d9aadf8344ede5d7a894db18647ffefaa486640cbac9d5b327- Stable URL of this page
https://metraipolis.com/documento/dc_e03b3da3bf53
How to cite
Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation — arXiv:2610.00678 — arXiv (en), https://arxiv.org/abs/2610.00678 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e03b3da3bf53 (Metraipolis archive dc_e03b3da3bf53, sha256 b34519e62d0340d9aadf8344ede5d7a894db18647ffefaa486640cbac9d5b327)
BibTeX
@misc{dce03b3da3bf53,
title = {Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation — arXiv:2610.00678},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00678},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e03b3da3bf53; sha256 b34519e62d0340d9aadf8344ede5d7a894db18647ffefaa486640cbac9d5b327},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00678. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Histological whole-slide images (WSIs) are central to computational pathology but pose severe computational challenges due to their extremely high resolution, often spanning several gigabytes per slide. To enable scalable learning, existing methods apply self-supervised data condensation to reduce computational cost, but typically rely on heuristic prototype learning and do not explicitly preserve learning-relevant feature distributions for downstream tasks. In response, we introduce a principled reformulation of WSI condensation as a distribution-matching problem under a fixed representational lens, and develop NICER, a tractable approximation framework based on a nonparametric prior with slide-adaptive capacity. Experiments on five histopathology datasets, together with clinical evaluation from a board-certified pathologist, show that NICER consistently outperforms prior methods, achieving an average accuracy improvement of 7.44% while offering improved efficiency-accuracy trade-offs, highlighting the benefits of principled, distribution-aware condensation for scalable histological representation learning. Source codes are available in this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in eess.IV). Categorie arXiv: Image and Video Processing (eess.IV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.00678 — 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 2026-10-07T12:12:01.109Z dalla pagina https://arxiv.org/catchup/eess.IV/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).