In this paper, we study the impact and role of multi-class labels on adversarial training for generative adversarial nets (GANs). Our derivation of the gradient shows that the current GAN model with labeled data still results in undesirable properties due to the overlay of the gradients from multiple classes. We thus argue that a better gradient should follow the intensity and direction that maximize each sample's activation on one and the only one class in each iteration, rather than weighted-averaging their gradients. We show, mathematically, that the proposed activation-maximized adversarial training (AM-GAN) is a general one covering two major complementary solutions exploring labeled information. Additionally, we investigate related metrics for evaluating generative models. Empirical experiments show that our approach has achieved the best Inception score (8.34) compared with previously reported results. Moreover, our adversarial training produces faster convergence with no mode collapse observed.

本文系统研究了当前使用类别标签的生成对抗网络GANs以及相关的分类信息对GAN网络的训练和生成效果的影响，并提出了一种新的基于激活最大化的AM-GAN生成对抗网络方案，在CIFAR-10数据集上实现了8.91的state-of-the-art Inception得分，并提出AM得分评价指标以更准确地评估生成样本质量。

激活极大化生成对抗网络