Title
Parallel Optimal Transport Gan
Abstract
Although Generative Adversarial Networks (GANs) are known for their sharp realism in image generation, they often fail to estimate areas of the data density. This leads to low modal diversity and at times distorted generated samples. These problems essentially arise from poor estimation of the distance metric responsible for training these networks. To address these issues, we introduce an additional regularisation term which performs optimal transport in parallel within a low dimensional representation space. We demonstrate that operating in a low dimension representation of the data distribution benefits from convergence rate gains in estimating the Wasserstein distance, resulting in more stable GAN training. We empirically show that our regulariser achieves a stabilising effect which leads to higher quality of generated samples and increased mode coverage of the given data distribution. Our method achieves significant improvements on the CIFAR-10, Oxford Flowers and CUB Birds datasets over several GAN baselines both qualitatively and quantitatively.
Year
DOI
Venue
2019
10.1109/CVPR.2019.00454
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
Field
DocType
ISSN
Computer vision,Computer science,Artificial intelligence
Conference
1063-6919
Citations 
PageRank 
References 
0
0.34
0
Authors
3
Name
Order
Citations
PageRank
Gil Avraham100.68
Yan Zuo202.03
Tom Drummond32676159.45