Multi-Task Learning for Visually Grounded Reasoning in Gastrointestinal VQA

TL;DR

This paper introduces a multi-task learning framework using a LoRA-tuned Florence-2 model for medical visual question answering, explanation, and grounding, achieving improved accuracy and interpretability in gastrointestinal VQA.

Contribution

It presents a novel multi-task approach combining VQA, explanation, and grounding with curated datasets, enhancing medical VQA performance and interpretability.

Findings

Significant improvement over single-task baselines in answer accuracy.

Enhanced visual grounding and interpretability.

Effective multi-task learning for medical VQA applications.

Abstract

We present a multi-task framework for the MediaEval Medico 2025 challenge, leveraging a LoRA-tuned Florence-2 model for simultaneous visual question answering (VQA), explanation generation, and visual grounding. The proposed system integrates three curated datasets: (1) Kvasir-VQA-x1 for question-answer learning, (2) a synthetically enriched explanation dataset offering structured medical reasoning, and (3) text-to-region pairs linking visual features with segmentation masks. This multi-task setup enables the model to jointly learn visual grounding, reasoning, and interpretation, producing responses that are both accurate and interpretable. Extensive evaluation demonstrates that our approach substantially improves over single-task baselines in both answer accuracy and visual localization, highlighting the effectiveness of grounded multi-task learning for medical VQA applications.