Generative adversarial network (GAN) has made great progress in image generation and reconstruction, but it may cause the mode collapse problem in practice. We proposed the dual discriminator weighted generative adversarial network (D2WGAN), whose objective function weights the Kullback–Leibler divergence (KL divergence) and the reverse KL divergence and uses the complementary characteristics of these two divergences to make the generated models more diverse. Moreover, we proved the theoretical conditional optimality of the D2WGAN to show that the generator can learn the real data distribution. Finally, we conduct experiments on a large amount of synthetic data and real-world datasets (e.g., MNIST and CIFAR-10). The results show that, compared with the traditional dual discriminator generative adversarial network and GAN, the proposed D2WGAN can process multiple mode data and generate better sample diversities.

中文翻译：

---

关于双重鉴别器加权生成对抗网络的有效性

生成对抗网络（GAN）在图像生成和重建方面取得了很大进展，但在实践中可能会导致模式崩溃问题。我们提出了双重鉴别器加权生成对抗网络（D2WGAN），其目标函数对 Kullback-Leibler 散度（KL 散度）和反向 KL 散度进行加权，并利用这两种散度的互补特性使生成的模型更加多样化。此外，我们证明了 D2WGAN 的理论条件最优性，以表明生成器可以学习真实的数据分布。最后，我们对大量合成数据和真实世界的数据集（例如，MNIST 和 CIFAR-10）进行了实验。结果表明，与传统的双鉴别器生成对抗网络和 GAN 相比，