1 code implementation • 17 Sep 2023 • Xiaoqing Zhang, Jilu Zhao, Yan Li, Hao Wu, Xiangtian Zhou, Jiang Liu
Moreover, motivated by the recent pretraining-and-finetuning paradigm, we attempt to adapt pre-trained natural image models for PM recognition by freezing them and treating the EPCA and other attention modules as adapters.
