GIFT: 一种面向视觉分类器全局可解释忠实文本解释的框架
GIFT: A Framework Towards Global Interpretable Faithful Textual Explanations of Vision Classifiers
AI总结：
GIFT提出一种框架，通过生成局部反事实并转化为文本解释，实现视觉分类器的全局可解释和忠实性。
摘要：
理解深度视觉模型的决策过程对于其在现实世界中的安全可靠部署至关重要。现有的可解释性方法，如显著性图或基于概念的分析，往往存在有限的忠实性、局部范围或语义模糊的问题。我们引入了GIFT，一种事后框架，旨在为视觉分类器推导出全局、可解释、忠实且文本化的解释。GIFT首先生成大量忠实的局部视觉反事实，然后利用视觉-语言模型将这些反事实转换为对视觉变化的自然语言描述。这些局部解释通过大型语言模型汇总为关于模型全局决策规则的简洁、可读的人类解释。关键的是，GIFT包含一个验证阶段，通过图像干预定量评估每个提出解释的因果效应，确保最终的文本解释忠实于模型的真实推理过程。在多样化的数据集上，包括合成CLEVR基准、现实中的CelebA面孔和复杂的BDD驾驶场景中，GIFT不仅揭示了有意义的分类规则，还揭示了驱动模型行为的意外偏见和潜在概念。总体而言，GIFT弥合了局部反事实推理和全局可解释性之间的差距，为视觉模型提供了基于因果的文本解释方法。
英文摘要：
Understanding the decision processes of deep vision models is essential for their safe and trustworthy deployment in real-world settings. Existing explainability approaches, such as saliency maps or concept-based analyses, often suffer from limited faithfulness, local scope, or ambiguous semantics. We introduce GIFT, a post-hoc framework that aims to derive Global, Interpretable, Faithful, and Textual explanations for vision classifiers. GIFT begins by generating a large set of faithful, local visual counterfactuals, then employs vision-language models to translate these counterfactuals into natural-language descriptions of visual changes. These local explanations are aggregated by a large language model into concise, human-readable hypotheses about the model's global decision rules. Crucially, GIFT includes a verification stage that quantitatively assesses the causal effect of each proposed explanation by performing image-based interventions, ensuring that the final textual explanations remain faithful to the model's true reasoning process. Across diverse datasets, including the synthetic CLEVR benchmark, the real-world CelebA faces, and the complex BDD driving scenes, GIFT reveals not only meaningful classification rules but also unexpected biases and latent concepts driving model behavior. Altogether, GIFT bridges the gap between local counterfactual reasoning and global interpretability, offering a principled approach to causally grounded textual explanations for vision models.
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。
