GIFT: A Framework for Global Interpretable Faithful Textual Explanations of Vision Classifiers
This work addresses the need for interpretable AI in safety-critical applications by providing a novel method for explaining vision classifiers, though it is incremental as it builds on existing local explanation techniques.
The authors tackled the problem of understanding deep vision classifiers by introducing GIFT, a framework that generates global, interpretable, and faithful textual explanations from local visual counterfactuals, with a verification stage to measure causal effects, and demonstrated its effectiveness across diverse datasets like CLEVR, CelebA, and BDD.
Understanding deep models is crucial for deploying them in safety-critical applications. We introduce GIFT, a framework for deriving post-hoc, global, interpretable, and faithful textual explanations for vision classifiers. GIFT starts from local faithful visual counterfactual explanations and employs (vision) language models to translate those into global textual explanations. Crucially, GIFT provides a verification stage measuring the causal effect of the proposed explanations on the classifier decision. Through experiments across diverse datasets, including CLEVR, CelebA, and BDD, we demonstrate that GIFT effectively reveals meaningful insights, uncovering tasks, concepts, and biases used by deep vision classifiers. The framework is released at https://github.com/valeoai/GIFT.