论文标题
通过对抗训练学习基于能量的模型
Learning Energy-Based Models With Adversarial Training
论文作者
论文摘要
我们研究了一种基于对抗性训练（AT）的基于能量的模型（EBM）的新方法。我们表明（二进制）学习一种特殊的能量功能，该功能对数据分布的支持进行了建模，并且学习过程与基于MCMC的EBM的最大似然学习密切相关。我们进一步提出了改进的与AT生成建模的技术，并证明这种新方法能够产生多样化和逼真的图像。除了具有竞争力的图像生成性能到明确的EBM外，研究的方法还可以稳定训练，非常适合图像翻译任务，并且表现出强大的分布外对抗性鲁棒性。我们的结果证明了AT生成建模方法的生存能力，这表明AT是学习EBM的竞争性替代方法。
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.
