论文标题
CDE-GAN:基于双重进化的合作生成对抗网络
CDE-GAN: Cooperative Dual Evolution Based Generative Adversarial Network
论文作者
论文摘要
生成对抗网络(GAN)一直是现实世界应用的流行深层生成模型。尽管最近在甘缝方面做出了许多贡献,但甘恩的模式崩溃和不稳定性仍然是由于其对抗性优化困难而引起的开放问题。在本文中,是由合作协同进化算法的动机,我们提出了一个基于合作双重进化的生成对抗网络(CDE-GAN)来避免这些弊端。从本质上讲,CDE-GAN将相对于发电机和歧视因子的双重演变纳入统一的进化对抗框架中,以进行有效的对抗性多目标优化。因此,它利用互补特性并将双重突变多样性注入训练中,以稳步多样化捕获多模型并改善生成性能的估计密度。具体而言,CDE-GAN将复杂的对抗优化问题分解为两个子问题(生成和歧视),并通过分离的亚群(E-Genererator}和E-E-Disciminators)解决了每个子问题,并通过其自身的进化算法而进化。此外,我们进一步提出了一种软机制,以平衡电子基因生成器和电子歧义者之间的权衡,以对CDE-GAN进行稳定的培训。对一个合成数据集和三个现实基准图像数据集进行了广泛的实验表明,所提出的CDE-GAN在生成优质质量和多样的样本上比基线实现了竞争性和卓越的性能。代码和更多生成的结果可在我们的项目主页上找到:https://shiming-chen.github.io/cde-gan-website/cde-gan.html。
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 multi-modes 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-Generator} and E-Discriminators), evolved by its own evolutionary algorithm. Additionally, we further propose a Soft Mechanism to balance the trade-off 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.