Robust Few-Shot Learning Without Using Any Adversarial Samples
The high cost of acquiring and annotating samples has made the “few-shot” learning
problem of prime importance. Existing works mainly focus on improving performance on …
problem of prime importance. Existing works mainly focus on improving performance on …
Understanding Adversarial Robustness From Feature Maps of Convolutional Layers
C Xu, W Zhang, J Wang, M Yang - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The adversarial robustness of a neural network mainly relies on two factors: model capacity
and antiperturbation ability. In this article, we study the antiperturbation ability of the network …
and antiperturbation ability. In this article, we study the antiperturbation ability of the network …