提出可自解释的图像生成模型，一键生成假设性修改建议。
The Gaussian Discriminant Variational Autoencoder (GdVAE): A Self-Explainable Model with Counterfactual Explanations
- 用条件变分自编码器构建可解释模型，结合高斯判别分析分类器
- 在潜空间中直接求解反事实解释，生成与原图高度相似的修改方案
- 适合需要透明决策过程的医疗、金融等高风险场景应用
视觉反事实解释（CF）方法通过修改图像中的概念（如形状）来改变预测结果，同时保持与原始查询图像的高度相似性。与自解释模型（SEMs）和热力图技术不同，它们使用户能够探究‘如果…会怎样’的假设情景。现有方法要么依赖事后训练，影响透明性与解释质量的平衡，要么需在推理时进行优化。为弥合透明性与反事实解释之间的差距，我们提出GdVAE，一种基于条件变分自编码器（CVAE）的自解释模型，配备高斯判别分析（GDA）分类器，并集成反事实解释功能。通过使用类特定原型完成下游任务，并在潜空间中提供反事实解释的闭式解，实现完全透明。通过解释函数对潜空间进行正则化，提升反事实解释的一致性。与现有方法的广泛对比证实，该方法能在保持透明性的同时生成高质量的反事实解释。代码与模型已公开。
原文摘要 · Abstract (English)
Visual counterfactual explanation (CF) methods modify image concepts, e.g, shape, to change a prediction to a predefined outcome while closely resembling the original query image. Unlike self-explainable models (SEMs) and heatmap techniques, they grant users the ability to examine hypothetical "what-if" scenarios. Previous CF methods either entail post-hoc training, limiting the balance between transparency and CF quality, or demand optimization during inference. To bridge the gap between transparent SEMs and CF methods, we introduce the GdVAE, a self-explainable model based on a conditional variational autoencoder (CVAE), featuring a Gaussian discriminant analysis (GDA) classifier and integrated CF explanations. Full transparency is achieved through a generative classifier that leverages class-specific prototypes for the downstream task and a closed-form solution for CFs in the latent space. The consistency of CFs is improved by regularizing the latent space with the explainer function. Extensive comparisons with existing approaches affirm the effectiveness of our method in producing high-quality CF explanations while preserving transparency. Code and models are public.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。