Metraipolis › archive › dc_13165589fa2b

EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment — arXiv:2608.04472

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04472
License (as archived)
CC0-1.0
Archived
2026-10-31T11:14:22.523Z
SHA-256 of the archived text
ab4bfa2ca7452570cc6c035b82165f43db70d58b462b8b017c5238bc220e8c1c
Stable URL of this page
https://metraipolis.com/documento/dc_13165589fa2b

How to cite

EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment — arXiv:2608.04472 — arXiv (en), https://arxiv.org/abs/2608.04472 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_13165589fa2b (Metraipolis archive dc_13165589fa2b, sha256 ab4bfa2ca7452570cc6c035b82165f43db70d58b462b8b017c5238bc220e8c1c)
BibTeX
@misc{dc13165589fa2b,
  title = {EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment — arXiv:2608.04472},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04472},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_13165589fa2b; sha256 ab4bfa2ca7452570cc6c035b82165f43db70d58b462b8b017c5238bc220e8c1c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04472. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The development of foundation models (FMs) is crucial for advancing endoscopic image analysis. However, existing endoscopy FMs mainly rely on self-supervised learning from uni-modal images or videos, overlooking the rich semantic knowledge contained in clinical reports. Furthermore, effectively leveraging these records is hindered by a fundamental modality gap: structured anatomical descriptions are not naturally mapped to specific frames within the high-redundancy, uncurated visual streams. In this paper, we present EndoVLM, a novel vision-language FM pre-trained on over 348K endoscopic examinations, each pairing a clinical report with its corresponding image collection. An Anatomy-Guided Sparse Pooling mechanism utilizes textual descriptions as queries to drive sparse attention, efficiently aggregating semantically salient frames into anatomy-specific visual representations across redundant image-sets. Next, a Progressive Semantic-Aware Alignment strategy models clinical taxonomy (anatomy and pathological status) via structured soft targets, bridging the gap from global patient-level matching to fine-grained localized alignment. Finally, a Semantic-Concentrated Masked Autoencoder is applied exclusively to these semantic-rich frames, integrating low-level visual precision with robust high-level semantic representation. Extensive experiments across various downstream tasks demonstrate that EndoVLM outperforms existing foundation models and remains competitive with task-specific methods. Remarkably, EndoVLM also exhibits robust zero-shot generalization capabilities, highlighting its potential for broader clinical application.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.04472 — 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 2026-10-31T11:02:13.519Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).