CDE-GAN: Cooperative dual evolution based generative adversarial network
Chen, S and Wang, W and Xia, B and You, X and Peng, Q and Cao, Z and Ding, W, CDE-GAN: Cooperative dual evolution based generative adversarial network, Ieee Transactions on Evolutionary Computation ISSN 1089-778X (In Press) [Refereed Article]
(c) 2021 IEEE
Generative adversarial networks (GANs) have been a popular deep generative model for real-world applications. Despite many recent efforts on GANs that have been contributed, mode collapse and instability of GANs are still open problems caused by their adversarial optimization difficulties. In this paper, motivated by the cooperative co-evolutionary algorithm, we propose a Cooperative Dual Evolution based Generative Adversarial Network (CDE-GAN) to circumvent these drawbacks. In essence, CDE-GAN incorporates dual evolution with respect to the generator(s) and discriminators into a unified evolutionary adversarial framework to conduct effective adversarial multi-objective optimization. Thus it exploits the complementary properties and injects dual mutation diversity into training to steadily diversify the estimated density in capturing multimodes and improve generative performance. Specifically, CDEGAN decomposes the complex adversarial optimization problem into two subproblems (generation and discrimination), and each subproblem is solved with a separated subpopulation (EGenerators and E-Discriminators), evolved by its own evolutionary algorithm. Additionally, to keep the balance between EGenerators and E-Discriminators, we further propose a Soft Mechanism to cooperate them to conduct effective multi-objective adversarial training. Extensive experiments on one synthetic dataset and three real-world benchmark image datasets demonstrate that the proposed CDE-GAN achieves a competitive and superior performance in generating good quality and diverse samples over baselines. The code and more generated results are available at our project homepage https://shiming-chen.github.io/ CDE-GAN-website/CDE-GAN.html.