Global Counterfactual Directions

arXiv:2404.12488v1 Announce Type: new
Abstract: Despite increasing progress in development of methods for generating visual counterfactual explanations, especially with the recent rise of Denoising Diffusion Probabilistic Models, previous works consider them as an entirely local technique. In this work, we take the first step at globalizing them. Specifically, we discover that the latent space of Diffusion Autoencoders encodes the inference process of a given classifier in the form of global directions. We propose a novel proxy-based approach that discovers two …

abstract arxiv autoencoders counterfactual cs.ai cs.cv cs.lg denoising development diffusion global progress space them type visual work