Concept-based Visual Counterfactual Explanations with Diffusion Models
Visual counterfactual explanations aim to answer "what minimal change to this image would flip the model's prediction?", and are increasingly important as vision models are deployed in safety-critical domains (e.g., medicine). Existing diffusion-based methods can produce realistic edits, but they rely on external classifiers that must work reliably on noisy images, which makes them fragile and hard to deploy for robust explanations. We introduce C-
By Yassine Oueslati, Daniil Kirilenko, Martin Gjoreski, Marc Langheinrich