用人类可理解的概念生成视觉模型的逻辑解释，既透明又准确。
Local-to-Global Logical Explanations for Deep Vision Models
- 将图像分类解释转化为单调析取范式逻辑公式，基于基础概念。
- 在复杂视觉数据集上保持高保真度与覆盖率，解释效果好。
- 支持单图和多图解释，适合需要可解释性的研究与应用。
深度神经网络虽在图像分类中表现卓越，但其决策过程难以解释。本文提出针对黑箱模型的局部与全局解释方法，以人类可识别的原始概念生成解释。无论是单张图像的局部解释，还是多张图像的全局解释，均被建模为单调析取范式（MDNF）逻辑公式，其满足条件即意味着模型对某类别得分较高。此外，还提出一种算法，用于解释多类别分类结果，输出基于原始概念的单调解释列表。尽管形式简洁且易于理解，这些解释在挑战性视觉数据集上仍保持了与原黑箱模型高度一致的保真度和覆盖范围。
原文摘要 · Abstract (English)
While deep neural networks are extremely effective at classifying images, they remain opaque and hard to interpret. We introduce local and global explanation methods for black-box models that generate explanations in terms of human-recognizable primitive concepts. Both the local explanations for a single image and the global explanations for a set of images are cast as logical formulas in monotone disjunctive-normal-form (MDNF), whose satisfaction guarantees that the model yields a high score on a given class. We also present an algorithm for explaining the classification of examples into multiple classes in the form of a monotone explanation list over primitive concepts. Despite their simplicity and interpretability we show that the explanations maintain high fidelity and coverage with respect to the blackbox models they seek to explain in challenging vision datasets.
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。