Diffusion-based Visual Counterfactual Explanations - Towards Systematic Quantitative Evaluation

  • 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.

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Philipp Väth, Alexander M. Frühwald, Benjamin Paaßen, Magda Gregorová
DOI:https://doi.org/10.48550/arXiv.2308.06100
Parent Title (English):CoRR
Document Type:Article
Language:English
Year of publication:2023
Release Date:2024/01/22
Volume:abs/2308.06100
Institutes and faculty:Fakultäten / Fakultät Informatik und Wirtschaftsinformatik
Institute / Center for Artificial Intelligence (CAIRO)
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.