2 papers
cs.CV2025
Disentangling Visual Transformers: Patch-level Interpretability for Image Classification
Guillaume Jeanneret, Loïc Simon, Frédéric Jurie
Visual transformers have achieved remarkable performance in image classification tasks, but this performance gain has come at the cost of interpretability. One of the main obstacle…
cs.CV2023
Text-to-Image Models for Counterfactual Explanations: a Black-Box Approach
Guillaume Jeanneret, Loïc Simon, Frédéric Jurie
This paper addresses the challenge of generating Counterfactual Explanations (CEs), involving the identification and modification of the fewest necessary features to alter a classi…