PacGAN: The Power of Two Samples in Generative Adversarial Networks
PacGAN: The Power of Two Samples in Generative Adversarial Networks
复制标题
DOI：
10.1109/jsait.2020.2983071
复制
发表时间：
2017-12
期刊：
影响因子：
--
通讯作者：
Zinan Lin;A. Khetan;G. Fanti;Sewoong Oh
中科院分区：
文献类型：
--
作者：
Zinan Lin;A. Khetan;G. Fanti;Sewoong Oh
生成对抗网络（GAN）是一种创新技术，用于从样本中学习复杂数据分布的生成模型。尽管在生成逼真的图像方面有了显着的改进，但它们的主要缺点之一是，在实践中，它们往往会生成几乎没有多样性的样本，即使在不同的数据集上进行训练。这种被称为模式崩溃的现象一直是GAN最近几项进展的主要焦点。然而，很少有人了解为什么模式崩溃发生，为什么最近提出的方法减轻模式崩溃。我们提出了一个原则性的方法来处理模式崩溃称为包装。其主要思想是修改神经网络，使其根据来自同一类的多个样本（无论是真实的还是人工生成的）做出决策。我们借用分析工具，从二元假设检验，特别是开创性的结果（Blackwell，1953年），以证明包装和模式崩溃之间的基本联系。我们表明，包装自然惩罚模式崩溃的发电机，从而有利于在训练过程中模式崩溃较少的发电机分布。在基准数据集上的数值实验表明，打包在实践中也提供了显着的改进。
Generative adversarial networks (GANs) are innovative techniques for learning generative models of complex data distributions from samples. Despite remarkable improvements in generating realistic images, one of their major shortcomings is the fact that in practice, they tend to produce samples with little diversity, even when trained on diverse datasets. This phenomenon, known as mode collapse, has been the main focus of several recent advances in GANs. Yet there is little understanding of why mode collapse happens and why recently-proposed approaches mitigate mode collapse. We propose a principled approach to handle mode collapse called packing. The main idea is to modify the discriminator to make decisions based on multiple samples from the same class, either real or artificially generated. We borrow analysis tools from binary hypothesis testing—in particular the seminal result of (Blackwell, 1953)—to prove a fundamental connection between packing and mode collapse. We show that packing naturally penalizes generators with mode collapse, thereby favoring generator distributions with less mode collapse during the training process. Numerical experiments on benchmark datasets suggests that packing provides significant improvements in practice as well.