AI RESEARCH
Dual Causal Inference: Integrating Backdoor Adjustment and Instrumental Variable Learning for Medical VQA
arXiv CS.CV
•
ArXi:2604.20306v1 Announce Type: new Medical Visual Question Answering (MedVQA) aims to generate clinically reliable answers conditioned on complex medical images and questions. However, existing methods often overfit to superficial cross-modal correlations, neglecting the intrinsic biases embedded in multimodal medical data. Consequently, models become vulnerable to cross-modal confounding effects, severely hindering their ability to provide trustworthy diagnostic reasoning. To address this limitation, we propose a novel Dual Causal Inference (DCI) framework for Med