论文标题
GAN训练中过度拟合和模式下降的经验分析
Empirical Analysis of Overfitting and Mode Drop in GAN Training
论文作者
论文摘要
我们从经验的角度研究了GAN培训中的两个关键问题，即过度拟合和模式下降。我们表明，当从训练过程中删除随机性时，甘恩可以过度fit，并且几乎没有模式下降。我们的结果阐明了GAN训练程序的重要特征。他们还提供了反对现行直觉的证据，表明甘斯不会记住训练集，并且该模式下降主要是由于gan目标的特性，而不是在训练过程中进行优化的方式。
We examine two key questions in GAN training, namely overfitting and mode drop, from an empirical perspective. We show that when stochasticity is removed from the training procedure, GANs can overfit and exhibit almost no mode drop. Our results shed light on important characteristics of the GAN training procedure. They also provide evidence against prevailing intuitions that GANs do not memorize the training set, and that mode dropping is mainly due to properties of the GAN objective rather than how it is optimized during training.
