Rethinking Visual Counterfactual Explanations Through Region Constraint

TL;DR

This paper introduces region-constrained visual counterfactual explanations (RVCEs) to improve interpretability by limiting modifications to specific image regions, addressing issues of entanglement and confirmation bias in previous methods.

Contribution

The paper proposes a novel region-constrained approach for visual counterfactual explanations and introduces RCSB, a new method based on Schr"odinger Bridges, achieving state-of-the-art results.

Findings

Achieves a large margin improvement over previous methods

Enables exact counterfactual reasoning within predefined regions

Allows user interaction for region specification

Abstract

Visual counterfactual explanations (VCEs) have recently gained immense popularity as a tool for clarifying the decision-making process of image classifiers. This trend is largely motivated by what these explanations promise to deliver -- indicate semantically meaningful factors that change the classifier's decision. However, we argue that current state-of-the-art approaches lack a crucial component -- the region constraint -- whose absence prevents from drawing explicit conclusions, and may even lead to faulty reasoning due to phenomenons like confirmation bias. To address the issue of previous methods, which modify images in a very entangled and widely dispersed manner, we propose region-constrained VCEs (RVCEs), which assume that only a predefined image region can be modified to influence the model's prediction. To effectively sample from this subclass of VCEs, we propose Region-Constrained Counterfactual Schr\"odinger Bridges (RCSB), an adaptation of a tractable subclass of Schr\"odinger Bridges to the problem of conditional inpainting, where the conditioning signal originates from the classifier of interest. In addition to setting a new state-of-the-art by a large margin, we extend RCSB to allow for exact counterfactual reasoning, where the predefined region contains only the factor of interest, and incorporating the user to actively interact with the RVCE by predefining the regions manually.