CDL-GAN: Contrastive Distance Learning Generative Adversarial Network for Image Generation

While Generative Adversarial Networks (GANs) have shown promising performance in image generation, they suffer from numerous issues such as mode collapse and training instability. To stabilize GAN training and improve image synthesis quality with diversity, we propose a simple yet effective approach...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2021-02, Vol.11 (4), p.1380
Main Authors: Zhou, Yingbo, Zhao, Pengcheng, Tong, Weiqin, Zhu, Yongxin
Format: Article
Language:English
Subjects:
characteristic contrastive distance
consistent contrastive distance
contrastive distance learning
Datasets
Distance learning
generative adversarial networks
Generators
Image processing
Image quality
Learning
Neural networks
Noise
Optimization techniques
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:While Generative Adversarial Networks (GANs) have shown promising performance in image generation, they suffer from numerous issues such as mode collapse and training instability. To stabilize GAN training and improve image synthesis quality with diversity, we propose a simple yet effective approach as Contrastive Distance Learning GAN (CDL-GAN) in this paper. Specifically, we add Consistent Contrastive Distance (CoCD) and Characteristic Contrastive Distance (ChCD) into a principled framework to improve GAN performance. The CoCD explicitly maximizes the ratio of the distance between generated images and the increment between noise vectors to strengthen image feature learning for the generator. The ChCD measures the sampling distance of the encoded images in Euler space to boost feature representations for the discriminator. We model the framework by employing Siamese Network as a module into GANs without any modification on the backbone. Both qualitative and quantitative experiments conducted on three public datasets demonstrate the effectiveness of our method.
ISSN:2076-3417
2076-3417
DOI:10.3390/app11041380