Generalization and Stability of GANs: A theory and promise from data augmentation
The instability when training generative adversarial networks (GANs) is a notoriously difficult issue, and the generalization of GANs remains open. In this paper, we will analyze various sources of instability which not only come from the discriminator but also the generator. We then point out that the requirement of Lipschitz continuity on both the discriminator and generator leads to generalization and stability for GANs. As a consequence, this work naturally provides a generalization bound for a large class of existing models and explains the success of recent large-scale generators. Finally, we show why data augmentation can ensure Lipschitz continuity on both the discriminator and generator. This work therefore provides a theoretical basis for a simple way to ensure generalization in GANs, explaining the highly successful use of data augmentation for GANs in practice.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationSimilar Papers 제목 키워드 기반
CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization
Generative Adversarial Networks (GANs) significantly advanced image generation but their performance heavily depends on abundant training data. In scenarios with limited data, GANs often struggle with discriminator overf…
Image GenerationGeneralization of GANs and overparameterized models under Lipschitz continuity
Generative adversarial networks (GANs) are so complex that the existing learning theories do not provide a satisfactory explanation for why GANs have great success in practice. The same situation also remains largely ope…
Data AugmentationGeneralization Bounds(q,p)-Wasserstein GANs: Comparing Ground Metrics for Wasserstein GANs
Generative Adversial Networks (GANs) have made a major impact in computer vision and machine learning as generative models. Wasserstein GANs (WGANs) brought Optimal Transport (OT) theory into GANs, by minimizing the $1$-…
Improving Generalization and Stability of Generative Adversarial Networks
Generative Adversarial Networks (GANs) are one of the most popular tools for learning complex high dimensional distributions. However, generalization properties of GANs have not been well understood. In this paper, we an…
Understanding and Stabilizing GANs' Training Dynamics with Control Theory
Generative adversarial networks (GANs) are effective in generating realistic images but the training is often unstable. There are existing efforts that model the training dynamics of GANs in the parameter space but the a…
Image GenerationL2 Regularization