Metraipolis › archive › dc_68bbeddd93f6

Test-Time Instance Selection for Improved Whole Slide Image Analysis — arXiv:2608.14759

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14759
License (as archived)
CC0-1.0
Archived
2026-10-19T02:05:57.730Z
SHA-256 of the archived text
94a76fc80cecf4ea4e72baefd292a5ef788e4d0a4d50fde459c10775c85298ae
Stable URL of this page
https://metraipolis.com/documento/dc_68bbeddd93f6

How to cite

Test-Time Instance Selection for Improved Whole Slide Image Analysis — arXiv:2608.14759 — arXiv (en), https://arxiv.org/abs/2608.14759 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_68bbeddd93f6 (Metraipolis archive dc_68bbeddd93f6, sha256 94a76fc80cecf4ea4e72baefd292a5ef788e4d0a4d50fde459c10775c85298ae)
BibTeX
@misc{dc68bbeddd93f6,
  title = {Test-Time Instance Selection for Improved Whole Slide Image Analysis — arXiv:2608.14759},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14759},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_68bbeddd93f6; sha256 94a76fc80cecf4ea4e72baefd292a5ef788e4d0a4d50fde459c10775c85298ae},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14759. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Whole Slide Image (WSI) analysis has been widely studied for cancer diagnosis. Conventionally, a gigapixel WSI is divided into small patches and processed by Multiple Instance Learning (MIL) models. However, existing MIL models typically process all patches, many of which contain redundant or non-informative tissue patterns. Although recent approaches have focused on instance selection to identify discriminative patches and reduce redundancy, these selection modules still require additional training. In this work, we propose Test-Time Instance Selection (TTIS), a training-free, plug-and-play framework that selects compact yet representative patches during inference. TTIS further incorporates a multi-view ensemble strategy to integrate distinct facets of tissue morphology, enhancing robustness. Importantly, TTIS can be seamlessly integrated into existing MIL models without retraining or architectural changes, enabling flexible deployment. Extensive evaluations across multiple benchmarks demonstrate that our approach improves or matches baseline MIL performance across a range of classification and subtyping tasks. Our implementation code is available at this https URL

Tema degli esploratori: scienze della vita e salute (retro-catalogo arXiv: annunci del 2026-08-18 in q-bio.QM).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV); Quantitative Methods (q-bio.QM).
Pagina del lavoro: https://arxiv.org/abs/2608.14759 — 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 2026-10-19T01:06:06.902Z dalla pagina https://arxiv.org/catchup/q-bio.QM/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).