AGAN: Towards Automated Design of Generative Adversarial Networks

Understand

Recent progress in Generative Adversarial Networks (GANs) has shown promising signs of improving GAN training via architectural change.

• Despite some early success, at present the design of GAN architectures requires human expertise, laborious trial-and-error testings, and often draws inspiration from its image classification counterpart.
• In the current paper, we present the first neural architecture search algorithm, automated neural architecture search for deep generative models, or AGAN for abbreviation, that is specifically suited for GAN training.
• For unsupervised image generation tasks on CIFAR-10, our algorithm finds architecture that outperforms state-of-the-art models under same regularization techniques.