Metraipolis › archive › dc_6b69a75eb6fb
EXPOSE: Explainable and Domain-Robust Embeddings from Pathology Vision Foundation Models using Sparse Autoencoders — arXiv:2608.28191
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28191
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T11:06:47.273Z
- SHA-256 of the archived text
15aebb5476d5b046160b99b40cb064c7371b87b582fc72450c3293801089ccb2- Stable URL of this page
https://metraipolis.com/documento/dc_6b69a75eb6fb
How to cite
EXPOSE: Explainable and Domain-Robust Embeddings from Pathology Vision Foundation Models using Sparse Autoencoders — arXiv:2608.28191 — arXiv (en), https://arxiv.org/abs/2608.28191 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6b69a75eb6fb (Metraipolis archive dc_6b69a75eb6fb, sha256 15aebb5476d5b046160b99b40cb064c7371b87b582fc72450c3293801089ccb2)
BibTeX
@misc{dc6b69a75eb6fb,
title = {EXPOSE: Explainable and Domain-Robust Embeddings from Pathology Vision Foundation Models using Sparse Autoencoders — arXiv:2608.28191},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28191},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6b69a75eb6fb; sha256 15aebb5476d5b046160b99b40cb064c7371b87b582fc72450c3293801089ccb2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28191. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision Foundation Models (VFMs) are widely used in computational pathology but remain sensitive to domain shifts arising from variations in staining, tissue preparation, and scanner hardware. A key limitation is that VFM embeddings entangle biological with domain-specific information, hindering cross-domain generalization. We propose Explainable Probing of Cross-Domain Sparse Embeddings (EXPOSE), a framework that uses Sparse Autoencoders (SAEs) as an explainable bottleneck to identify and suppress domain-specific components in VFM embeddings. We train a sparse representation of VFM features, use a linear classifier to identify domain-specific latent dimensions, and mask these features prior to downstream relapse prediction without retraining the backbone model. Experiments on a large prostate cancer dataset with multiple acquisition domains show that SAE features capture both domain- and task-specific information, which are partially disentangled in the latent space. Removing domain-specific features improves cross-domain performance and increases embedding robustness as measured by the Domain Robustness Index (DoRI). Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.28191 — 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 2026-10-17T10:50:25.847Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).