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(GAN)在各种任务和应用中都展现出了引人注目的结果。然而,模式崩溃仍然是GAN中的一个关键问题。在本文中,我们提出了一种新颖的训练流程来解决GAN的模式崩溃问题。不同于现有的方法,我们提出将判别器作为特征嵌入器进行泛化,并最大化由其学习的嵌入空间中的分布熵。具体而言,我们设计了两个正则化项,即深度局部线性嵌入(DLLE)和深度等距特征映射(DIsoMap),以鼓励判别器学习嵌入在数据中的结构信息,从而形成良好的嵌入空间。基于由判别器支持的良好学习的嵌入空间,我们设计了一个非参数熵估计器,以有效最大化嵌入向量的熵,作为最大化生成分布熵的近似估计。通过提高判别器和最大化嵌入空间中最相似样本的距离,我们的训练流程有效地减少了模式崩溃,而不会牺牲生成样本的质量。大量的实验结果表明了我们方法的有效性,它优于CelebA数据集上的基线GAN、MaF-GAN(9.13 vs. 12.43 in FID),并在ANIME-FACE数据集上超过了最近的最先进能量模型(2.80 vs. 2.26 in Inception score)。代码可在https://github.com/HaozheLiu-ST/MEE获得。