Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Tasks

1 code implementation • ICML Workshop AML 2021 • Fan Liu, Shuyu Zhao, Xuelong Dai, Bin Xiao

Although adversarial training (AT) methods such as Adversarial Query (AQ) can improve the adversarially robust performance of meta-learning models, AT is still computationally expensive training.

Adversarial Robustness Classification +1