AI RESEARCH
Uncertainty-Aware Information Pursuit for Interpretable and Reliable Medical Image Analysis
arXiv CS.CV
•
ArXi:2506.16742v3 Announce Type: replace To be adopted in safety-critical domains like medical image analysis, AI systems must provide human-interpretable decisions. Variational Information Pursuit (V-IP) offers an interpretable-by-design framework by sequentially querying input images for human-understandable concepts, using their presence or absence to make predictions. However, existing V-IP methods overlook sample-specific uncertainty in concept predictions, which can arise from ambiguous features or model limitations, leading to suboptimal query selection and reduced robustness.