Adversarial Margin Maximization Networks
Published in Oct, 2019
Yan, Ziang, Yiwen Guo, and Changshui Zhang. "Adversarial Margin Maximization Networks." PAMI 2019.
In this paper, we analyze the generalization ability of DNNs comprehensively and attempt to improve it from a geometric point of view. We propose adversarial margin maximization (AMM), a learning-based regularization which exploits an adversarial perturbation as a proxy. It encourages a large margin in the input space, just like the support vector machines.