The principle of generative adversarial net is to fit the given data distribution by combining a generative model and discriminative model. There are two major challenges to conventional systems – they are difficult to train and they easily fall into ‘mode collapse’. To improve it, this study describes a novel network structure with dual generators. A ‘cooperation’ mechanism is introduced to help the generators work together. During training, generators not only learn from discriminative feedback but also from each other (like a study group). Compared with a single-generator network, a dual-generator network could capture many more ‘modes’ and eventually reduce the impact of ‘mode collapse.’ Dual networks also require extra computational resources. However, our experiment shows that even with network parameters of similar size, dual networks still achieved better results. Additionally, a dual-generator structure could be extended to multiple generators. The proposed network structure is also very robust and flexible. It can be adapted to various application scenarios, such as high-resolution image generation, domain adaptation and 3D model generation. The experimental results showed that with the same computing resources, multiple generators can generate better quality synthetic data, including 2D images, 3D objects, style transferring etc.

中文翻译：

---

合作：双网络结构增强对抗性对抗网络的新力量

生成对抗网络的原理是通过组合生成模型和判别模型来拟合给定的数据分布。常规系统有两个主要挑战–难以训练，很容易陷入“模式崩溃”。为了改进它，本研究描述了一种具有双发生器的新型网络结构。引入了“合作”机制来帮助发电机一起工作。在培训过程中，生成器不仅从歧视性反馈中学习，而且还彼此学习（就像学习小组一样）。与单发电机网络相比，双发电机网络可以捕获更多的“模式”，并最终减少“模式崩溃”的影响。双网络也需要额外的计算资源。但是，我们的实验表明，即使网络参数的大小相似，双网仍然取得了较好的效果。另外，双发电机结构可以扩展到多个发电机。所提出的网络结构也非常健壮和灵活。它可以适应各种应用场景，例如高分辨率图像生成，域自适应和3D模型生成。实验结果表明，使用相同的计算资源，多个生成器可以生成质量更好的合成数据，包括2D图像，3D对象，样式转换等。