Generative Adversarial Networks (GANs) have shown compelling results in various tasks and applications in recent years. However, mode collapse remains a critical problem in GANs. In this paper, we propose a novel training pipeline to address the mode collapse issue of GANs. Different from existing methods, we propose to generalize the discriminator as feature embedding and maximize the entropy of distributions in the embedding space learned by the discriminator. Specifically, two regularization terms, i.e., Deep Local Linear Embedding (DLLE) and Deep Isometric feature Mapping (DIsoMap), are designed to encourage the discriminator to learn the structural information embedded in the data, such that the embedding space learned by the discriminator can be well-formed. Based on the well-learned embedding space supported by the discriminator, a non-parametric entropy estimator is designed to efficiently maximize the entropy of embedding vectors, playing as an approximation of maximizing the entropy of the generated distribution. By improving the discriminator and maximizing the distance of the most similar samples in the embedding space, our pipeline effectively reduces the mode collapse without sacrificing the quality of generated samples. Extensive experimental results show the effectiveness of our method, which outperforms the GAN baseline, MaF-GAN on CelebA (9.13 vs. 12.43 in FID) and surpasses the recent state-of-the-art energy-based model on the ANIME-FACE dataset (2.80 vs. 2.26 in Inception score). The code is available at https://github.com/HaozheLiu-ST/MEE

翻译：生成对抗网络（GANs）近年来在各种任务和应用中展现出显著成果。然而，模式崩溃仍然是GANs面临的关键问题。本文提出一种新颖的训练流程来解决GANs的模式崩溃问题。与现有方法不同，我们提出将判别器泛化为特征嵌入，并最大化判别器所学习嵌入空间中分布的熵。具体而言，我们设计了两种正则化项，即深度局部线性嵌入（DLLE）和深度等距特征映射（DIsoMap），以促使判别器学习数据中蕴含的结构信息，从而使判别器学习的嵌入空间具有良好的结构。基于判别器支撑的良好学习嵌入空间，我们设计了一种非参数熵估计器，用于高效最大化嵌入向量的熵，这近似于最大化生成分布的熵。通过改进判别器并最大化嵌入空间中最相似样本之间的距离，我们的流程有效减少了模式崩溃，同时不牺牲生成样本的质量。大量实验结果表明了本方法的有效性，在CelebA数据集上优于GAN基线模型MaF-GAN（FID值9.13 vs. 12.43），并在ANIME-FACE数据集上超越最新基于能量的模型（Inception评分2.80 vs. 2.26）。代码已开源在https://github.com/HaozheLiu-ST/MEE。