IEEE Trans Pattern Anal Mach Intell. 2022 May;44(5):2657-2672. doi: 10.1109/TPAMI.2020.3043745. Epub 2022 Apr 1.
The generator in generative adversarial networks (GANs) is driven by a discriminator to produce high-quality images through an adversarial game. At the same time, the difficulty of reaching a stable generator has been increased. This paper focuses on non-adversarial generative networks that are trained in a plain manner without adversarial loss. The given limited number of real images could be insufficient to fully represent the real data distribution. We therefore investigate a set of distributions in a Wasserstein ball centred on the distribution induced by the training data and propose to optimize the generator over this Wasserstein ball. We theoretically discuss the solvability of the newly defined objective function and develop a tractable reformulation to learn the generator. The connections and differences between the proposed non-adversarial generative networks and GANs are analyzed. Experimental results on real-world datasets demonstrate that the proposed algorithm can effectively learn image generators in a non-adversarial approach, and the generated images are of comparable quality with those from GANs.
生成对抗网络（GANs）中的生成器受到判别器的驱动，通过对抗博弈产生高质量的图像。同时，生成器达到稳定的难度也增加了。本文重点研究的是在没有对抗损失的情况下，以简单方式训练的非对抗生成网络。给定的有限数量的真实图像可能不足以充分表示真实数据分布。因此，我们研究了一组以训练数据诱导的分布为中心的Wasserstein 球中的分布，并提出在这个 Wasserstein 球上优化生成器。我们从理论上讨论了新定义的目标函数的可解性，并开发了一个可处理的重构来学习生成器。分析了所提出的非对抗生成网络与 GAN 之间的联系和区别。在真实数据集上的实验结果表明，所提出的算法可以有效地以非对抗的方式学习图像生成器，生成的图像质量与 GAN 生成的图像相当。
