论文标题
反事实解释的扩散模型
Diffusion Models for Counterfactual Explanations
论文作者
论文摘要
反事实解释已显示出令人鼓舞的结果，作为事后框架，使图像分类器更具解释。在本文中，我们提出了一角钱，这是一种允许使用最近的扩散模型生成反事实图像的方法。通过利用引导的生成扩散过程，我们提出的方法可以显示如何使用目标分类器的梯度来生成输入实例的反事实解释。此外，我们分析了当前的方法来评估虚假相关性，并通过提出新的指标：相关差异来扩展评估测量。我们的实验验证表明，所提出的算法超过了Celeba 6个指标中的5个指标的先前最新结果。
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.
