Skip to content
AI News HubLIVE
Original source2 min read

QCAP-VQA: Question-Conditioned Capped Prior-Mass Supervision for Medical Visual Question Answering

Summary

QCAP-VQA supervises a subset of cross-attention heads with a question-conditioned prior from ranked segmentation proposals, using a capped prior-mass objective that penalizes insufficient attention only below a threshold. It matches baseline accuracy while increasing attention on annotated structures, but prior-referenced and expert-referenced evaluations rank models in largely opposite order.

SourcearXiv Computer VisionAuthor: Yining Zhao, Catarina Moreira, Mukesh Prasad, Ali Braytee
QCAP-VQA: Question-Conditioned Capped Prior-Mass Supervision for Medical Visual Question Answering
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 13 Nov 2026]

Title:QCAP-VQA: Question-Conditioned Capped Prior-Mass Supervision for Medical Visual Question Answering

View a PDF of the paper titled QCAP-VQA: Question-Conditioned Capped Prior-Mass Supervision for Medical Visual Question Answering, by Yining Zhao and 3 other authors

View PDF HTML (experimental)

Abstract:Medical visual question answering models can answer correctly without attending to the anatomy that the question names. Automatic region priors allow spatial supervision without expert masks, but they are noisy, and it is unclear how strongly they should shape attention and how their effect should be verified. We present QCAP-VQA, which supervises a subset of cross-attention heads with a question-conditioned prior built from ranked segmentation proposals. Its capped prior-mass objective penalizes insufficient attention inside the prior only below a threshold. We evaluate attention against SLAKE structure boxes that play no role in training, separating attention on the named anatomy from how attention shifts between questions about the same image. QCAP-VQA matches the accuracy of a baseline without spatial supervision (84.26% vs. 84.23%), and every evaluated prior-supervised model places more attention on the annotated structures. Over a 64-fold range of regularization strength, the capped objective keeps prior mass between 0.67 and 0.77, whereas a pooled region-mass objective drives it to 0.97 and loses accuracy. The cost lies in question conditioning: as the constraint widens or strengthens, attention shifts agree less with the expert-defined contrast. Across 13 configurations, prior-referenced and expert-referenced evaluation rank the models in largely opposite order (Spearman correlation of -0.87), and the capped models it favors track the prior's own errors. Because clinical use of medical visual question answering requires answers grounded in the queried anatomy, supervision from automatic priors should be judged against independent anatomical references.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2611.17708 [cs.CV]

(or arXiv:2611.17708v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.17708

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yining Zhao [view email] [v1] Fri, 13 Nov 2026 03:36:34 UTC (1,510 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled QCAP-VQA: Question-Conditioned Capped Prior-Mass Supervision for Medical Visual Question Answering, by Yining Zhao and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • QCAP-VQA uses a question-conditioned prior from ranked segmentation proposals to supervise a subset of cross-attention heads.
  • The capped objective keeps prior mass between 0.67 and 0.77 over a 64-fold regularization range, while a pooled region-mass objective drives it to 0.97 and loses accuracy.
  • Prior-referenced and expert-referenced evaluations yield a Spearman correlation of -0.87 across 13 configurations, ranking models in largely opposite order.
  • Supervision from automatic priors should be judged against independent anatomical references because capped models track the prior's own errors.

Highlights and analysis are generated automatically and may contain errors. Check the original source.