In order to alleviate the notorious mode collapse phenomenon in generative adversarial networks (GANs), we propose a novel training method of GANs in which certain fake samples are considered as real ones during the training process. This strategy can reduce the gradient value that generator receives in the region where gradient exploding happens. We show the process of an unbalanced generation and a vicious circle issue resulted from gradient exploding in practical training, which explains the instability of GANs. We also theoretically prove that gradient exploding can be alleviated by penalizing the difference between discriminator outputs and fake-as-real consideration for very close real and fake samples. Accordingly, Fake-As-Real GAN (FARGAN) is proposed with a more stable training process and a more faithful generated distribution. Experiments on different datasets verify our theoretical analysis.
翻译:为了缓解基因对抗网络中臭名昭著的模式崩溃现象,我们提议对基因对抗网络采用一种新的培训方法,在培训过程中将某些假样品视为真实样品;这一战略可以降低梯度爆炸发生地区生成器的梯度值;我们展示了不平衡的一代过程,以及实际培训中的梯度爆炸造成的恶性循环问题,这解释了基因对抗网络的不稳定性;我们还从理论上证明,通过惩罚歧视产物与假冒真实考虑之间的差别,可以减轻梯度爆炸。因此,提议采用更稳定的培训过程和更加忠实的分布法,对假冒的真真真假样品进行惩罚。关于不同数据集的实验证实了我们的理论分析。