Generative Adversarial Parallelization
Generative Adversarial Parallelization
复制标题
DOI：
--
复制
发表时间：
2016-11
期刊：
影响因子：
--
通讯作者：
Daniel Jiwoong Im;He Ma;C. Kim;Graham W. Taylor
中科院分区：
文献类型：
--
作者：
Daniel Jiwoong Im;He Ma;C. Kim;Graham W. Taylor
生成对抗网络由于其直观的公式化，已成为无监督学习中研究最多的框架之一。它们也被证明能够在有限的领域（如低分辨率图像）中生成令人信服的示例。然而，它们仍然难以在实践中训练，并且倾向于忽略数据生成分布的模式。量化捕获效果，如模式覆盖率和更一般的生成模型的质量仍然难以捉摸。我们提出了生成式对抗神经元化，这是一个框架，在这个框架中，许多GAN或它们的变体同时被训练，交换它们的判别器。这消除了发生器和振荡器之间的紧密耦合，从而改善了收敛性和模式覆盖范围。我们还提出了最近提出的生成对抗度量的改进变体，并展示了它如何在差距模型下对单个GAN或其集合进行评分。
Generative Adversarial Networks have become one of the most studied frameworks for unsupervised learning due to their intuitive formulation. They have also been shown to be capable of generating convincing examples in limited domains, such as low-resolution images. However, they still prove difficult to train in practice and tend to ignore modes of the data generating distribution. Quantitatively capturing effects such as mode coverage and more generally the quality of the generative model still remain elusive. We propose Generative Adversarial Parallelization, a framework in which many GANs or their variants are trained simultaneously, exchanging their discriminators. This eliminates the tight coupling between a generator and discriminator, leading to improved convergence and improved coverage of modes. We also propose an improved variant of the recently proposed Generative Adversarial Metric and show how it can score individual GANs or their collections under the GAP model.