Score: 0

Towards Desiderata-Driven Design of Visual Counterfactual Explainers

Published: June 17, 2025 | arXiv ID: 2506.14698v1

By: Sidney Bender , Jan Herrmann , Klaus-Robert Müller and more

Potential Business Impact:

Shows how to change pictures to fool computers.

Business Areas:
Visual Search Internet Services

Visual counterfactual explainers (VCEs) are a straightforward and promising approach to enhancing the transparency of image classifiers. VCEs complement other types of explanations, such as feature attribution, by revealing the specific data transformations to which a machine learning model responds most strongly. In this paper, we argue that existing VCEs focus too narrowly on optimizing sample quality or change minimality; they fail to consider the more holistic desiderata for an explanation, such as fidelity, understandability, and sufficiency. To address this shortcoming, we explore new mechanisms for counterfactual generation and investigate how they can help fulfill these desiderata. We combine these mechanisms into a novel 'smooth counterfactual explorer' (SCE) algorithm and demonstrate its effectiveness through systematic evaluations on synthetic and real data.

Page Count
18 pages

Category
Computer Science:
Machine Learning (CS)