用更合理的损失函数让GAN训练变简单，性能还更强。
The GAN is dead; long live the GAN! A Modern GAN Baseline
- 设计新损失函数，解决模式崩溃和不收敛问题。
- 去掉所有经验技巧，用现代架构提升性能。
- 简化后仍优于主流GAN和扩散模型，适合研究参考。
有观点认为GAN难以训练且依赖大量经验技巧。本文提供反例，并以更系统的方式构建现代GAN基线。首先，推导出一种具有良好性质的正则化相对式GAN损失，解决了以往需依赖随意技巧才能处理的模式缺失与不收敛问题；该损失经数学分析，证明具有局部收敛保证，优于多数现有相对式损失。其次，新损失使我们可抛弃所有经验性技巧，改用现代网络结构替代传统骨干。以StyleGAN2为例，提出简化与现代化路径，形成新基线R3GAN。尽管结构极简，其在FFHQ、ImageNet、CIFAR及Stacked MNIST数据集上的表现超越StyleGAN2，且媲美当前顶尖GAN与扩散模型。
原文摘要 · Abstract (English)
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 Second, our new loss allows us to discard all ad-hoc tricks and replace outdated backbones used in common GANs with modern architectures.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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。