There is a widely-spread claim that GANs are difficult to train, and GAN architectures in the literature are littered with empirical tricks. We provide evidence against this claim and build a modern GAN baseline in a more principled manner. First, we derive a well-behaved regularized relativistic GAN loss that addresses issues of mode dropping and non-convergence that were previously tackled via a bag of ad-hoc tricks. We analyze our loss mathematically and prove that it admits local convergence guarantees, unlike most existing relativistic losses. Second, our new loss allows us to discard all ad-hoc tricks and replace outdated backbones used in common GANs with modern architectures. Using StyleGAN2 as an example, we present a roadmap of simplification and modernization that results in a new minimalist baseline -- R3GAN. Despite being simple, our approach surpasses StyleGAN2 on FFHQ, ImageNet, CIFAR, and Stacked MNIST datasets, and compares favorably against state-of-the-art GANs and diffusion models.

本研究解决了关于GAN训练难度的普遍看法，提出了一种更为原则化的现代GAN基线。通过推导出新的正则化相对GAN损失，该损失不仅解决了模式丢失和不收敛的问题，还确保了局部收敛性。R3GAN作为简化的基线模型，尽管设计简单，但在多个数据集上的表现超过了现有的StyleGAN2，表明其潜在的影响力和实用性。

GAN已死，GAN万岁！一种现代化的GAN基线