Localized Questions in Medical Visual Question Answering

TL;DR

This paper introduces a new medical VQA model capable of answering region-specific questions within images, enhancing interpretability and accuracy over existing whole-image focused models.

Contribution

It presents a novel model that answers questions about specific image regions in medical VQA, improving interpretability and performance.

Findings

Outperforms existing methods on three datasets

Enhances interpretability by focusing on image regions

Demonstrates effectiveness through experimental results

Abstract

Visual Question Answering (VQA) models aim to answer natural language questions about given images. Due to its ability to ask questions that differ from those used when training the model, medical VQA has received substantial attention in recent years. However, existing medical VQA models typically focus on answering questions that refer to an entire image rather than where the relevant content may be located in the image. Consequently, VQA models are limited in their interpretability power and the possibility to probe the model about specific image regions. This paper proposes a novel approach for medical VQA that addresses this limitation by developing a model that can answer questions about image regions while considering the context necessary to answer the questions. Our experimental results demonstrate the effectiveness of our proposed model, outperforming existing methods on three datasets. Our code and data are available at https://github.com/sergiotasconmorales/locvqa.