CoLa-DCE——概念引导的潜在扩散反事实解释
CoLa-DCE -- Concept-guided Latent Diffusion Counterfactual Explanations
AI总结：
提出CoLa-DCE方法，利用概念引导的潜在扩散模型为图像分类器生成高可控、高粒度的反事实解释，通过最小特征变化提升透明度与可理解性。
摘要：
生成式AI的最新进展带来了新的前景和实际应用。特别是扩散模型在生成多样化且逼真特征方面展现出优势，使其非常适合为计算机视觉模型生成反事实解释。反事实解释通过回答“需要改变什么才能使图像分类器改变预测”这一“如果”问题，与人类理解高度契合，从而有助于使模型行为更易于理解。当前方法虽能生成真实的反事实，但缺乏透明度，因为特征变化无法直接被感知。为解决这一局限，我们提出了概念引导的潜在扩散反事实解释（CoLa-DCE）。CoLa-DCE能够为任意分类器生成概念引导的反事实，在概念选择和空间条件控制方面具有高度可控性。这些反事实通过最小特征变化实现了更高的粒度。参考特征可视化确保了更好的可理解性，而特征定位则提高了关于“在哪里”改变了“什么”的透明度。我们在多个图像分类模型和数据集上展示了该方法在最小化和可理解性方面的优势，并深入探讨了CoLa-DCE解释如何帮助理解诸如误分类等模型错误。
英文摘要：
Recent advancements in generative AI have introduced novel prospects and practical implementations. Especially diffusion models show their strength in generating diverse and, at the same time, realistic features, positioning them well for generating counterfactual explanations for computer vision models. Answering "what if" questions of what needs to change to make an image classifier change its prediction, counterfactual explanations align well with human understanding and consequently help in making model behavior more comprehensible. Current methods succeed in generating authentic counterfactuals, but lack transparency as feature changes are not directly perceivable. To address this limitation, we introduce Concept-guided Latent Diffusion Counterfactual Explanations (CoLa-DCE). CoLa-DCE generates concept-guided counterfactuals for any classifier with a high degree of control regarding concept selection and spatial conditioning. The counterfactuals comprise an increased granularity through minimal feature changes. The reference feature visualization ensures better comprehensibility, while the feature localization provides increased transparency of "where" changed "what". We demonstrate the advantages of our approach in minimality and comprehensibility across multiple image classification models and datasets and provide insights into how our CoLa-DCE explanations help comprehend model errors like misclassification cases.
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。
