AttCAT: Explaining Transformers via Attentive Class Activation Tokens

Published in NeurIPS, 2022

Use Google Scholar for full citation

Citation: Yao Qiang, Deng Pan, Chengyin Li, Xin Li, Rhongho Jang, Dongxiao Zhu, "AttCAT: Explaining Transformers via Attentive Class Activation Tokens." In the proceedings of NeurIPS, 2022.