Uncertainty-Aware Subset Selection for Robust Visual Explainability under Distribution Shifts

ArXi:2512.08445v2 Announce Type: replace-cross Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image regions and object-level explanations. While these methods perform well in in-distribution (ID) settings, their behavior under out-of-distribution (OOD) conditions remains poorly understood. Through extensive experiments across multiple ID-OOD sets, we find that reliability of the existing subset based methods degrades markedly, yielding redundant, unstable, and uncertainty-sensitive explanations.