A fundamental and still largely unsolved question in the context of Generative Adversarial Networks is whether they are truly able to capture the real data distribution and, consequently, to sample from it. In particular, the multidimensional nature of image distributions leads to a complex evaluation of the diversity of GAN distributions. Existing approaches provide only a partial understanding of this issue, leaving the question unanswered. In this work, we introduce a loop-training scheme for the systematic investigation of observable shifts between the distributions of real training data and GAN generated data. Additionally, we introduce several bounded measures for distribution shifts, which are both easy to compute and to interpret. Overall, the combination of these methods allows an explorative investigation of innate limitations of current GAN algorithms. Our experiments on different data-sets and multiple state-of-the-art GAN architectures show large shifts between input and output distributions, showing that existing theoretical guarantees towards the convergence of output distributions appear not to be holding in practice.
翻译:在Genement Aversarial Network中,一个基本和基本上尚未解决的问题是,它们是否真正能够捕捉到真实的数据分布,从而从中提取样本。特别是,图像分布的多面性导致对GAN分布多样性的复杂评估。现有方法只提供部分了解这一问题,而没有回答问题。在这项工作中,我们引入了一个循环培训计划,系统调查真实培训数据分布与GAN生成的数据之间的可观测变化。此外,我们引入了若干关于分布变化的约束性措施,这些措施既容易计算,也容易解释。总体而言,这些方法的结合使得人们能够对当前GAN算法的内在局限性进行探索性调查。我们在不同的数据集和多种最先进的GAN结构方面的实验显示,投入和产出分布之间的巨大变化表明,目前关于产出分布趋同的理论保证在实践中似乎并不存在。