# Sparse Visual Counterfactual Explanations in Image Space

Source: [Sparse Visual Counterfactual Explanations in Image Space](<https://www.sota2.com/research/paper/68fa6dc11e209131cea3be00>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:42:13.334Z

Authors: Valentyn Boreiko, Maximilian Augustin, Francesco Croce, Philipp Berens, Matthias Hein

Published: 2022-05-16T20:23:11.000Z

## Abstract

Visual counterfactual explanations (VCEs) in image space are an important tool to understand decisions of image classifiers as they show under which changes of the image the decision of the classifier would change. Their generation in image space is challenging and requires robust models due to the problem of adversarial examples. Existing techniques to generate VCEs in image space suffer from spurious changes in the background. Our novel perturbation model for VCEs together with its efficient optimization via our novel Auto-Frank-Wolfe scheme yields sparse VCEs which lead to subtle changes specific for the target class. Moreover, we show that VCEs can be used to detect undesired behavior of ImageNet classifiers due to spurious features in the ImageNet dataset.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2205.07972>)

[PDF](<https://arxiv.org/pdf/2205.07972.pdf>)