论文标题
在生成对抗网络中打击模式崩溃的分配拟合
Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networks
论文作者
论文摘要
模式崩溃是生成对抗网络的重要问题。在这项工作中，我们从新颖的角度研究了模式崩溃的原因。由于训练过程中的不均匀采样，在采样数据时可能会丢失一些子分布。结果，即使生成的分布与真实的分布不同，GAN目标仍然可以达到最小值。为了解决该问题，我们提出了一种全球分配拟合（GDF）方法，其中限制了生成的数据分布。当生成的分布与真实分布不同时，GDF将使目标更难达到最小值，而原始的全局最小值不会更改。为了处理总体真实数据无法到达的情况时，我们还提出了局部分配拟合（LDF）方法。几个基准的实验证明了GDF和LDF的有效性和竞争性能。
Mode collapse is a significant unsolved issue of generative adversarial networks. In this work, we examine the causes of mode collapse from a novel perspective. Due to the nonuniform sampling in the training process, some sub-distributions may be missed when sampling data. As a result, even when the generated distribution differs from the real one, the GAN objective can still achieve the minimum. To address the issue, we propose a global distribution fitting (GDF) method with a penalty term to confine the generated data distribution. When the generated distribution differs from the real one, GDF will make the objective harder to reach the minimal value, while the original global minimum is not changed. To deal with the circumstance when the overall real data is unreachable, we also propose a local distribution fitting (LDF) method. Experiments on several benchmarks demonstrate the effectiveness and competitive performance of GDF and LDF.
