Metraipolis › archive › dc_e6002ed31f87

Gated Prototype Transfer for Zero-Support Medical Vision Language Model — arXiv:2610.28350

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.28350
License (as archived)
CC0-1.0
Archived
2026-10-21T07:08:25.211Z
SHA-256 of the archived text
f108e62146080cf451e014e65772e15b670e34a071b69cd62975669aca31a16d
Stable URL of this page
https://metraipolis.com/documento/dc_e6002ed31f87

How to cite

Gated Prototype Transfer for Zero-Support Medical Vision Language Model — arXiv:2610.28350 — arXiv (en), https://arxiv.org/abs/2610.28350 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e6002ed31f87 (Metraipolis archive dc_e6002ed31f87, sha256 f108e62146080cf451e014e65772e15b670e34a071b69cd62975669aca31a16d)
BibTeX
@misc{dce6002ed31f87,
  title = {Gated Prototype Transfer for Zero-Support Medical Vision Language Model — arXiv:2610.28350},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.28350},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e6002ed31f87; sha256 f108e62146080cf451e014e65772e15b670e34a071b69cd62975669aca31a16d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.28350. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Realistic few-shot adaptation of medical vision-language models (VLMs) can leave low-prevalence classes without any labeled support. The training-free SS- Text+ solver remains operational in this setting, but its zero-support prototypes receive no visual adaptation and fall back to a purely textual class prototype. We in- troduce Gated Knowledge-Guided Prototype Transfer (GProtoT), a pre-repulsion module that transfers supported-class visual residuals to missing classes using VLM similarity and an ontology-based clinical distance. A validation-free evidence gate scales transfer based on semantic relevance and residual agreement, thereby limiting unsupported extrapolation. In 50 paired realistic one-shot trials on MESSIDOR with FLAIR features, severe and proliferative diabetic retinopathy were absent from every support set. Relative to SS-Text+, gated ProtoT improved missing-class recall by 5.23 points, average class accuracy by 1.37 points, and the missing/supported recall harmonic mean by 1.83 points. It reduced negative- transfer frequency from 46-48% for ungated transfer to 2%, while at the cost of reductions of 1.20 percentage points in supported-class recall and 0.45 percentage points in top-1 accuracy. These results indicate that evidence-based gating provides a safety mechanism for the knowledge source. GProtoT is based on SS- Text+ and requires no gradients, validation data, or additional model inference, of- fering a low-compute path toward accountable adaptation under incomplete clini- cal supervision. Code is available: 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/2610.28350 — 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 2026-10-21T07:05:43.642Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).