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

TL;DR

This paper introduces an uncertainty-aware subset selection framework that enhances the robustness and fidelity of visual explanations for deep vision models, especially under out-of-distribution conditions, without extra training.

Contribution

It proposes a novel method combining submodular selection with gradient-based uncertainty estimation to improve explanation stability and informativeness under distribution shifts.

Findings

Reduces redundancy and instability in explanations under OOD

Improves explanation quality in in-distribution settings

Enhances trustworthiness of visual model explanations

Abstract

Subset selection-based methods are widely used to explain deep vision models: they attribute predictions by highlighting the most influential image regions and support 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. To address these shortcomings, we introduce a framework that combines submodular subset selection with layer-wise, gradient-based uncertainty estimation to improve robustness and fidelity without requiring additional training or auxiliary models. Our approach estimates uncertainty via adaptive weight perturbations and uses these estimates to guide submodular optimization, ensuring diverse and informative subset selection. Empirical evaluations show that, beyond mitigating the weaknesses of existing methods under OOD scenarios, our framework also yields improvements in ID settings. These findings highlight limitations of current subset-based approaches and demonstrate how uncertainty-driven optimization can enhance attribution and object-level interpretability, paving the way for more transparent and trustworthy AI in real-world vision applications.