Clarity: an improved gradient method for producing quality visual counterfactual explanations

TL;DR

This paper introduces Clarity, a new gradient-based method utilizing generative models and ensemble classifiers in latent space to generate high-quality, realistic visual counterfactual explanations for image classifiers.

Contribution

The paper presents Clarity, a novel classification model that improves gradient quality for visual counterfactuals using generative models and ensemble training in latent space.

Findings

Clarity produces realistic counterfactual explanations across all images.

The techniques outperform existing methods in explanation quality.

Selecting a meaningful input space is crucial for effective counterfactual generation.

Abstract

Visual counterfactual explanations identify modifications to an image that would change the prediction of a classifier. We propose a set of techniques based on generative models (VAE) and a classifier ensemble directly trained in the latent space, which all together, improve the quality of the gradient required to compute visual counterfactuals. These improvements lead to a novel classification model, Clarity, which produces realistic counterfactual explanations over all images. We also present several experiments that give insights on why these techniques lead to better quality results than those in the literature. The explanations produced are competitive with the state-of-the-art and emphasize the importance of selecting a meaningful input space for training.