Many variants of adversarial training have been proposed, with most research focusing on problems with relatively few classes. In this paper, we propose Two Head Adversarial Training (THAT), a two-stream adversarial learning network that is designed to handle the large-scale many-class ImageNet dataset. The proposed method trains a network with two heads and two loss functions; one to minimize feature-space domain shift between natural and adversarial images, and one to promote high classification accuracy. This combination delivers a hardened network that achieves state of the art robust accuracy while maintaining high natural accuracy on ImageNet. Through extensive experiments, we demonstrate that the proposed framework outperforms alternative methods under both standard and "free" adversarial training settings.

翻译：提出了许多对抗性培训的变式,大多数研究侧重于相对较少班级的问题。在本文中,我们提议建立双头对抗性培训(THAT),这是一个双流对抗性学习网络,旨在处理大型多级图像网络数据集。拟议方法培训一个有两个头和两个损失功能的网络;一个是最大限度地减少自然和对抗性图像之间的地貌空间域变化,另一个是提高分类准确性。这种组合提供了一种硬化的网络,在保持图像网络高度自然准确性的同时,实现了最新水平的准确性。通过广泛的实验,我们证明拟议的框架超越了标准和“免费”对抗性培训环境中的替代方法。