Abstract
Despite the popularity of Vision Transformers (ViTs) and eXplainable AI (XAI), only a few explanation methods have been proposed for ViTs thus far. They use attention weights of the classification token on patch embeddings and often produce unsatisfactory saliency maps. In this paper, we propose a novel method for explaining ViTs called ViT-CX. It is based on patch embeddings, rather than attentions paid to them, and their causal impacts on the model output. ViT-CX can be used to explain different ViT models. Empirical results show that, in comparison with previous methods, ViT-CX produces more meaningful saliency maps and does a better job at revealing all the important evidence for prediction. It is also significantly more faithful to the model as measured by deletion AUC and insertion AUC.
Abstract (translated)
URL
https://arxiv.org/abs/2211.03064
