Regularizing Generative Adversarial Networks under Limited Data

Regularizing Generative Adversarial Networks under Limited Data Hung-Yu Tseng 2   Lu Jiang 1   Ce Liu 1   Ming-Hsuan Yang 1,2,3   Weilong Yang 1 1Google Research   2UC Merced   3Yonsei University Abstract Recent years have witnessed the rapid progress of generative adversarial networks (GANs). However, the success of the GAN models hinges on a large amount of training data. This work proposes a regularization approach for training robust GAN models on limited data. We theoretically show a co

Date: 2021/04/08 03:19

Related Entries

Read more [2009.08319] Decoupling Representation Learning from Reinforcement Learningopen searchopen navigatio...
0 users, 6 mentions 2020/09/18 08:21
Read more Real-Time High-Resolution Background Matting
0 users, 6 mentions 2020/12/15 14:21
Read more [2101.01321] I-BERT: Integer-only BERT Quantization
0 users, 4 mentions 2021/01/06 20:21
Read more [2102.00719] Video Transformer Network
0 users, 4 mentions 2021/02/02 17:22
Read more User-Guided Line Art Flat Filling with Split Filling Mechanism
0 users, 2 mentions 2021/03/19 15:51