Metraipolis › archive › dc_a3a7a38afa68

OpenMidnight: Closing the Performance Gap Between Open and Proprietary Pathology Foundation Models — arXiv:2611.00064

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00064
License (as archived)
CC0-1.0
Archived
2026-11-03T11:40:19.269Z
SHA-256 of the archived text
595f7fe1ae6ff368399de96ecf031dc9681fbf500e374c5fcecad18c57ac176a
Stable URL of this page
https://metraipolis.com/documento/dc_a3a7a38afa68

How to cite

OpenMidnight: Closing the Performance Gap Between Open and Proprietary Pathology Foundation Models — arXiv:2611.00064 — arXiv (en), https://arxiv.org/abs/2611.00064 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a3a7a38afa68 (Metraipolis archive dc_a3a7a38afa68, sha256 595f7fe1ae6ff368399de96ecf031dc9681fbf500e374c5fcecad18c57ac176a)
BibTeX
@misc{dca3a7a38afa68,
  title = {OpenMidnight: Closing the Performance Gap Between Open and Proprietary Pathology Foundation Models — arXiv:2611.00064},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00064},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a3a7a38afa68; sha256 595f7fe1ae6ff368399de96ecf031dc9681fbf500e374c5fcecad18c57ac176a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00064. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pathology foundation models offer transferable representations for a range of downstream tasks in computational pathology, but reliance on proprietary data, substantial compute requirements, and limited availability of training code and preprocessing pipelines hinder independent validation and further methodological development. We present OpenMidnight 1.1, an open-source replication and refinement of Midnight trained on approximately 12,000 publicly available whole-slide images from The Cancer Genome Atlas. Using an encoder initialized with pretrained DINOv2 weights, OpenMidnight 1.1 uses approximately 320 H100 GPU-hours for pathology pretraining, a 34-fold reduction relative to the compute reported for Midnight. Across 16 classification and four segmentation datasets in THUNDER, OpenMidnight 1.1 achieves the highest mean segmentation Dice (69.7) and ranks fourth among 14 models, ahead of Midnight, with performance that matches or exceeds models trained on substantially larger datasets in several tasks. Our ablation studies additionally examine how initialization, data volume, model size, and tissue composition affect downstream performance, providing empirical evidence to inform the development of future training recipes. Our release of the training code, preprocessing pipeline, and model weights lowers barriers to reproducible research and further development of competitive pathology foundation models.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.00064 — 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 2026-11-03T11:06:37.375Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).