Improving GAN Training with Probability Ratio Clipping and Sample Reweighting Yue Wu1, Pan Zhou 2, Andrew Gordon Wilson

Neural Information Processing Systems 

Despite success on a wide range of problems related to vision, generative adversarial networks (GANs) often suffer from inferior performance due to unstable training, especially for text generation.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found