"Defensive Few-shot Learning" by Wenbin Li, Lei Wang et al.
This paper investigates a new challenging problem called defensive few-shot learning in order to learn a robust few-shot model against adversarial attacks. Simply applying the existing adversarial defense methods to few-shot learning cannot effectively solve this problem. This is because the commonly assumed sample-level distribution consistency between the training and test sets can no longer be met in the few-shot setting. To address this situation, we develop a general defensive few-shot lear...
Adversarial Attacks Convolutional Neural Networks Efensive Few Shot Learning Distribution Consistency Pisodic Training Graphics Processing Units
Source: uow.edu.au