[08-06-2023] Diffusion Models for Counterfactual Explanations
Diffusion Models for Counterfactual Explanations, Guillaume Jeanneret, Loïc Simon, and Fr ́ed ́eric Jurie,ACCV2022 link
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 measure- ments by proposing a new metric: Correlation Difference. Our experi- mental validations show that the proposed algorithm surpasses previous state-of-the-art results on 5 out of 6 metrics on CelebA.
Si ça vous dit je peux aussi présenter https://arxiv.org/pdf/2303.09962.pdf en même temps.