Diffusion Models for Counterfactual Explanations - GREYC image Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Diffusion Models for Counterfactual Explanations

Résumé

Counterfactual explanations have shown promising results as a post-hoc framework to make image classifiers more explainable. In this paper, we propose DiME, a method allowing the generation of counterfactual images using the recent diffusion models. By leveraging the guided generative diffusion process, our proposed methodology shows how to use the gradients of the target classifier to generate counterfactual explanations of input instances. Further, we analyze current approaches to evaluate spurious correlations and extend the evaluation measurements by proposing a new metric: Correlation Difference. Our experimental validations show that the proposed algorithm surpasses previous State-of-the-Art results on 5 out of 6 metrics on CelebA.
Fichier principal
Vignette du fichier
ACCV_2022_DiME_camera_ready.pdf (726.83 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04583065 , version 1 (27-05-2024)

Identifiants

Citer

Guillaume Jeanneret, Loïc Simon, Frédéric Jurie. Diffusion Models for Counterfactual Explanations. 16th Asian Conference on Computer Vision (ACCV2022), Dec 2022, Macao, China. ⟨10.1007/978-3-031-26293-7_14⟩. ⟨hal-04583065⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More