PEGANs: Phased Evolutionary Generative Adversarial Networks with Self-Attention Module
Open Access
- 5 August 2022
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 10 (15) , 2792
Abstract
Generative adversarial networks have made remarkable achievements in generative tasks. However, instability and mode collapse are still frequent problems. We improve the framework of evolutionary generative adversarial networks (E-GANs), calling it phased evolutionary generative adversarial networks (PEGANs), and adopt a self-attention module to improve upon the disadvantages of convolutional operations. During the training process, the discriminator will play against multiple generators simultaneously, where each generator adopts a different objective function as a mutation operation. Every time after the specified number of training iterations, the generator individuals will be evaluated and the best performing generator offspring will be retained for the next round of evolution. Based on this, the generator can continuously adjust the training strategy during training, and the self-attention module also enables the model to obtain the modeling ability of long-range dependencies. Experiments on two datasets showed that PEGANs improve the training stability and are competitive in generating high-quality samples.Keywords
Funding Information
- National Natural Science Foundation of China (61876089, 61876185, 61902281, BK20141005)
- Natural Science Foundation of Jiangsu Province (61876089, 61876185, 61902281, BK20141005)
This publication has 13 references indexed in Scilit:
- Evolutionary Architectural Search for Generative Adversarial NetworksIEEE Transactions on Emerging Topics in Computational Intelligence, 2022
- CDE-GAN: Cooperative Dual Evolution-Based Generative Adversarial NetworkIEEE Transactions on Evolutionary Computation, 2021
- MirrorGAN: Learning Text-To-Image Generation by Redescription2019
- Evolutionary Generative Adversarial NetworksIEEE Transactions on Evolutionary Computation, 2019
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks2019
- Multi-agent Diverse Generative Adversarial Networks2018
- Non-local Neural Networks2018
- Least Squares Generative Adversarial Networks2017
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network2017