Diffusion-based Visual Counterfactual Explanations -- Towards Systematic Quantitative Evaluation

TL;DR

This paper introduces a systematic framework and metrics for quantitatively evaluating diffusion-based visual counterfactual explanations, enabling consistent comparison and analysis of different methods on ImageNet classifiers.

Contribution

It proposes a standardized evaluation framework and metrics for VCE methods, addressing the lack of consistent assessment procedures in the field.

Findings

Diffusion-based VCEs can be systematically evaluated using the proposed metrics.

Design choices in generative models significantly impact VCE quality.

The methodology facilitates reproducibility and transparency in VCE research.

Abstract

Latest methods for visual counterfactual explanations (VCE) harness the power of deep generative models to synthesize new examples of high-dimensional images of impressive quality. However, it is currently difficult to compare the performance of these VCE methods as the evaluation procedures largely vary and often boil down to visual inspection of individual examples and small scale user studies. In this work, we propose a framework for systematic, quantitative evaluation of the VCE methods and a minimal set of metrics to be used. We use this framework to explore the effects of certain crucial design choices in the latest diffusion-based generative models for VCEs of natural image classification (ImageNet). We conduct a battery of ablation-like experiments, generating thousands of VCEs for a suite of classifiers of various complexity, accuracy and robustness. Our findings suggest multiple directions for future advancements and improvements of VCE methods. By sharing our methodology and our approach to tackle the computational challenges of such a study on a limited hardware setup (including the complete code base), we offer a valuable guidance for researchers in the field fostering consistency and transparency in the assessment of counterfactual explanations.