DuC-GAN:增强GAN训练稳定性的新模型

DuC-GAN:a Novel Model for Enhancing GAN Training Stability

针对生成对抗网络(GAN)训练不稳定的问题,提出了一种新的双循环GAN(DuC-GAN)增强稳定性的模型。该模型通过在生成器和判别器之间添加额外的循环来解决GAN训练中的不稳定性问题。新循环由一个冻结的主判别器和一个辅助判别器组成,他们与生成器一起进行训练,并以生成器的性能作为切换循环的指标。在多个数据集上的测试表明,相比现有模型,所提模型显著提高了GAN的性能和训练稳定性。实验结果表明,双循环GAN实现了更快的收敛速度和更好的生成效果。

We propose a new model,called"dual-cycle generative adversarial networks(DuC-GAN)"to enhance the stability of training in generative adversarial networks(GAN).The framework addresses the issue of training instability in GAN by introducing an additional cycle between the generator and discriminator.This new cycle is composed of a frozen original discriminator and a new discriminator,both of which are trained together with the generator and switched based on the generator's performance.Testing on multiple datasets has proved that the proposed framework significantly improves the performance and training stability of GAN compared to available model,achieving faster convergence and better generation quality.