Generative adversarial networks have achieved remarkable performance on various tasks but suffer from training instability. Despite many training strategies proposed to improve training stability, this issue remains as a challenge. In this paper, we investigate the training instability from the perspective of adversarial samples and reveal that adversarial training on fake samples is implemented in vanilla GANs, but adversarial training on real samples has long been overlooked. Consequently, the discriminator is extremely vulnerable to adversarial perturbation and the gradient given by the discriminator contains non-informative adversarial noises, which hinders the generator from catching the pattern of real samples. Here, we develop adversarial symmetric GANs (AS-GANs) that incorporate adversarial training of the discriminator on real samples into vanilla GANs, making adversarial training symmetrical. The discriminator is therefore more robust and provides more informative gradient with less adversarial noise, thereby stabilizing training and accelerating convergence. The effectiveness of the AS-GANs is verified on image generation on CIFAR-10, CIFAR-100, CelebA, and LSUN with varied network architectures. Not only the training is more stabilized, but the FID scores of generated samples are consistently improved by a large margin compared to the baseline. Theoretical analysis is also conducted to explain why AS-GAN can improve training. The bridging of adversarial samples and adversarial networks provides a new approach to further develop adversarial networks.

生成式对抗网络在各种任务上均取得了卓越的性能，但训练不稳定。尽管提出了许多提高训练稳定性的训练策略，但是这个问题仍然是一个挑战。在本文中，我们从对抗性样本的角度研究了训练的不稳定性，并揭示了在伪装样本中进行对抗性训练是在香草GAN中进行的，但对真实样本的对抗性训练却长期以来被忽略了。因此，鉴别器极易受到对抗性扰动的影响，并且鉴别器给出的梯度包含非情报性对抗噪声，这阻碍了生成器捕捉真实样本的模式。这里，我们开发了对抗对称GAN（AS-GAN），该技术将对真实样本上的鉴别器的对抗训练纳入香草GAN中，从而使对抗训练变得对称。因此，鉴别器更加健壮，并提供了更多的信息梯度，而对抗性噪声却更少，从而稳定了训练并加速了收敛。在具有各种网络体系结构的CIFAR-10，CIFAR-100，CelebA和LSUN上生成图像时，已验证了AS-GAN的有效性。与基线相比，不仅训练更加稳定，而且所生成样本的FID分数也得到了持续改善。还进行了理论分析，以解释AS-GAN为什么可以改善培训。对抗性样本和对抗性网络之间的桥梁为进一步发展对抗性网络提供了一种新方法。