Combating Mode Collapse via Offline Manifold Entropy Estimation

Abstract

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 introduced 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 ANIMEFACE dataset (2.80 vs. 2.26 in Inception score).

Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks

“…To alleviate the data sparsity or imbalance issue, traditional data augmentation techniques for GANs (Zhao et al 2020;Karras et al 2020;Tran et al 2021;Jiang et al 2021;Tseng et al 2021;Liu et al 2023) often employ geometric transformations on real images, such as flipping, translation, and rotation, to guide GANs in learning "what to generate". However, Sinha et al (2021) introduced a distinctive approach, known as Negative Data Augmentation (NDA), for unconditional or class-conditional GANs.…”