Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa. Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature Alignment. In Luc De Raedt, editor, Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23-29 July 2022. pages 1009-1016, ijcai.org, 2022. [doi]
Abstract is missing.