# MF2-MVQA: A Multi-stage Feature Fusion method for Medical Visual Question Answering

Source: [MF2-MVQA: A Multi-stage Feature Fusion method for Medical Visual Question Answering](<https://www.sota2.com/research/paper/68fa6de71e209131cea3cd36>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:46:11.149Z

Authors: Shanshan Song, Jiangyun Li, Jing Wang, Yuanxiu Cai, Wenkai Dong

Published: 2022-11-11T04:11:07.000Z

## Abstract

There is a key problem in the medical visual question answering task that how to effectively realize the feature fusion of language and medical images with limited datasets. In order to better utilize multi-scale information of medical images, previous methods directly embed the multi-stage visual feature maps as tokens of same size respectively and fuse them with text representation. However, this will cause the confusion of visual features at different stages. To this end, we propose a simple but powerful multi-stage feature fusion method, MF2-MVQA, which stage-wise fuses multi-level visual features with textual semantics. MF2-MVQA achieves the State-Of-The-Art performance on VQA-Med 2019 and VQA-RAD dataset. The results of visualization also verify that our model outperforms previous work.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2211.05991>)

[PDF](<https://arxiv.org/pdf/2211.05991.pdf>)