Metraipolis › archive › dc_92f8dca6c440

VoluCompose: Constructing Compact Volumetric Visual Representations for Medical Image Understanding — arXiv:2611.08649

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08649
License (as archived)
CC0-1.0
Archived
2026-11-09T22:34:27.658Z
SHA-256 of the archived text
fd07001f313a975a6933b9de6c1a83194a981425a5d5afe771ced085c2502eba
Stable URL of this page
https://metraipolis.com/documento/dc_92f8dca6c440

How to cite

VoluCompose: Constructing Compact Volumetric Visual Representations for Medical Image Understanding — arXiv:2611.08649 — arXiv (en), https://arxiv.org/abs/2611.08649 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_92f8dca6c440 (Metraipolis archive dc_92f8dca6c440, sha256 fd07001f313a975a6933b9de6c1a83194a981425a5d5afe771ced085c2502eba)
BibTeX
@misc{dc92f8dca6c440,
  title = {VoluCompose: Constructing Compact Volumetric Visual Representations for Medical Image Understanding — arXiv:2611.08649},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08649},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_92f8dca6c440; sha256 fd07001f313a975a6933b9de6c1a83194a981425a5d5afe771ced085c2502eba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08649. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Medical vision--language models can interpret volumetric images, but processing full volumes is costly because hundreds of slices produce long, redundant visual-token sequences. Existing compression methods often couple content selection with budget determination. We observe that neighboring slices share visual features and that attention concentration varies across visual encoders. We propose VoluCompose, a training-free, model-agnostic framework that separates what visual content to retain from how many tokens to allocate. Its hyperbolic token composition module groups contiguous slices into ordered support units and uses the Lorentz distance to account for feature magnitude and direction during token allocation, anchor selection, and refinement. Its capacity control module uses visual-encoder attention entropy to allocate more tokens when attention is more dispersed. We evaluate VoluCompose on two tasks across three datasets and four backbones. Across nine calibrated settings, VoluCompose attains the highest mean quality--retention hypervolume among the compared methods. It achieves a mean relative quality of 121.68\% against the uncompressed references while retaining 22.78% of visual tokens on average. Compression remains robust even at a 10% token budget. Across settings, the lowest ROUGE-L ratio to the uncompressed reference is 96.4\% for VoluCompose. The corresponding minima for the compression baselines range from 15.0% to 70.5%. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.08649 — 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 2026-11-09T22:30:47.301Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).