图像回归器的扩散反事实解释
Diffusion Counterfactuals for Image Regressors
AI总结：
本文提出两种基于扩散模型的反事实生成方法，分别作用于像素空间和潜在空间，用于图像回归任务，以生成稀疏且高质量的解释，并揭示虚假相关性。
摘要：
反事实解释已被成功应用于为各种黑盒模型创建人类可解释的解释。它们在图像领域的任务中非常有用，因为解释的质量得益于生成模型的最新进展。尽管反事实解释已广泛应用于分类模型，但其在回归任务中的应用仍未得到充分探索。我们提出了两种方法，利用基于扩散的生成模型为图像回归任务创建反事实解释，以应对稀疏性和质量方面的挑战：1）一种基于直接在像素空间操作的去噪扩散概率模型；2）另一种基于在潜在空间操作的扩散自编码器。两种方法在CelebA-HQ和合成数据集上均能产生逼真、语义化且平滑的反事实，为回归模型的决策过程提供易于解释的见解，并揭示虚假相关性。我们发现，对于回归反事实，特征的变化取决于预测值的区域。预测值的显著变化需要大的语义变化，这使得找到稀疏反事实比分类器更难。此外，像素空间的反事实更稀疏，而潜在空间的反事实质量更高，并允许更大的语义变化。
英文摘要：
Counterfactual explanations have been successfully applied to create human interpretable explanations for various black-box models. They are handy for tasks in the image domain, where the quality of the explanations benefits from recent advances in generative models. Although counterfactual explanations have been widely applied to classification models, their application to regression tasks remains underexplored. We present two methods to create counterfactual explanations for image regression tasks using diffusion-based generative models to address challenges in sparsity and quality: 1) one based on a Denoising Diffusion Probabilistic Model that operates directly in pixel-space and 2) another based on a Diffusion Autoencoder operating in latent space. Both produce realistic, semantic, and smooth counterfactuals on CelebA-HQ and a synthetic data set, providing easily interpretable insights into the decision-making process of the regression model and reveal spurious correlations. We find that for regression counterfactuals, changes in features depend on the region of the predicted value. Large semantic changes are needed for significant changes in predicted values, making it harder to find sparse counterfactuals than with classifiers. Moreover, pixel space counterfactuals are more sparse while latent space counterfactuals are of higher quality and allow bigger semantic changes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
