Gradient Normalization for Generative Adversarial Networks

2 code implementations • ICCV 2021 • Yi-Lun Wu, Hong-Han Shuai, Zhi-Rui Tam, Hong-Yu Chiu

In this paper, we propose a novel normalization method called gradient normalization (GN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space.

Attractive or Faithful? Popularity-Reinforced Learning for Inspired Headline Generation

1 code implementation • 6 Feb 2020 • Yun-Zhu Song, Hong-Han Shuai, Sung-Lin Yeh, Yi-Lun Wu, Lun-Wei Ku, Wen-Chih Peng

To generate inspired headlines, we propose a novel framework called POpularity-Reinforced Learning for inspired Headline Generation (PORL-HG).

Headline Generation Reinforcement Learning (RL) +1