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 article, motivated by the cooperative co-evolutionary algorithm, we propose a cooperative dual evolution-based GAN (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 multiobjective optimization. Thus, it exploits the complementary properties and injects dual mutation diversity into the training, to steadily diversify the estimated density in capturing multimodes and improve generative performance. Specifically, CDE-GAN decomposes the complex adversarial optimization problem into two subproblems (generation and discrimination), and each subproblem is solved with a separated subpopulation ( E-Generators and E-Discriminators ), evolved by its own evolutionary algorithm. Additionally, we further propose a Soft Mechanism to balance the tradeoff between E-Generators and E-Discriminators to conduct steady training for CDE-GAN. 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 .

中文翻译：

---

CDE-GAN：基于协同双进化的生成对抗网络

生成对抗网络 (GAN) 已成为现实世界应用中流行的深度生成模型。尽管最近在 GAN 上做出了许多努力，但 GAN 的模式崩溃和不稳定性仍然是由其对抗性优化困难引起的开放性问题。在本文中，受合作协同进化算法的启发，我们提出了一种基于合作对偶进化的 GAN（CDE-GAN）来规避这些缺点。本质上，CDE-GAN 将生成器和判别器的双重进化结合到一个统一的进化对抗框架中，以进行有效的对抗多目标优化。因此，它利用互补特性并将双重变异多样性注入训练，在捕获多模时稳定地多样化估计密度并提高生成性能。具体来说，CDE-GAN 将复杂的对抗优化问题分解为两个子问题（生成和判别），每个子问题用分离的子种群（ 电子发电机和 E-Discriminators ），由它自己的进化算法进化而来。此外，我们进一步提出了一个平衡 E-Generator 和 E-Discriminator 之间权衡的软机制，以对 CDE-GAN 进行稳定的训练。在一个合成数据集和三个真实世界基准图像数据集上进行的大量实验表明，所提出的 CDE-GAN 在生成高质量和不同基线样本方面取得了具有竞争力和卓越的性能。代码和更多生成的结果可以在我们的项目主页上找到https://shiming-chen.github.io/CDE-GAN-website/CDE-GAN.html .