Improving GAN training with probability ratio clipping and sample reweighting

• Main Authors: WU, Yue, ZHOU, Pan, GORDON, Andrew Wilson, XING, Eric, HU, Zhiting
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2020
• 主題: Graphics and Human Computer Interfaces
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/8996; https://ink.library.smu.edu.sg/context/sis_research/article/9999/viewcontent/2020_NeurIPS_GAN.pdf

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. To solve this issue, we propose a new variational GAN training framework which enjoys superior traini...