AI RESEARCH
Learning Quantifiable Visual Explanations Without Ground-Truth
arXiv CS.LG
•
ArXi:2605.18681v1 Announce Type: cross Explainable AI (XAI) techniques are increasingly important for the validation and responsible use of modern deep learning models, but are difficult to evaluate due to the lack of good ground-truth to compare against. We propose a framework that serves as a quantifiable metric for the quality of XAI methods, based on continuous input perturbation.