We study a new approach to learning energy-based models (EBMs) based on adversarial training (AT). We show that (binary) AT learns a special kind of energy function that models the support of the data distribution, and the learning process is closely related to MCMC-based maximum likelihood learning of EBMs. We further propose improved techniques for generative modeling with AT, and demonstrate that this new approach is capable of generating diverse and realistic images. Aside from having competitive image generation performance to explicit EBMs, the studied approach is stable to train, is well-suited for image translation tasks, and exhibits strong out-of-distribution adversarial robustness. Our results demonstrate the viability of the AT approach to generative modeling, suggesting that AT is a competitive alternative approach to learning EBMs.
翻译:我们研究了一种基于对抗性培训的学习基于能源模型的新方法。我们表明(二进制)AT学会一种特殊的能源功能,这种功能可以模拟数据分布的支持,学习过程与基于MCMC的EBM最大可能性学习密切相关。我们进一步建议采用AT的改良型模型技术,并表明这种新方法能够产生多样化和现实的图像。除了向明确的EBM提供有竞争力的图像生成性能外,所研究的方法还可以稳定地进行培训,适合于图像转换任务,并展示出强大的分配外对抗性强。我们的结果表明AT的组合型模型方法是可行的,表明AT是学习EBM的竞争性替代方法。