AGAN: Towards Automated Design of Generative Adversarial Networks

2019/06/25 by Hanchao Wang, Wang, Hanchao, Jun Huan +1
Computer Science · Mathematics · #Advanced Image Processing Techniques #Artificial Intelligence (cs.AI) #Digital Media Forensic Detection #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.AI #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1906.11080

arxiv created 2019/06/25 · openalex publication_date 2019/06/25 · arxiv updated 2019/06/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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. For supervised tasks, the automatically searched architectures also achieve highly competitive performance, outperforming best human-invented architectures at resolution 32×32. Moreover, we empirically demonstrate that the modules learned by AGAN are transferable to other image generation tasks such as STL-10.

Citations

• Conditional Generative Adversarial Nets
• Improved Techniques for Training GANs
• Neural Architecture Search with Reinforcement Learning
• Improved Training of Wasserstein GANs
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Class-Splitting Generative Adversarial Networks
• Progressive Neural Architecture Search
• Efficient Neural Architecture Search via Parameter Sharing
• Path-Level Network Transformation for Efficient Architecture Search
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Efficient Architecture Search by Network Transformation
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Related

• AutoGAN: Neural Architecture Search for Generative Adversarial Networks
• AdversarialNAS: Adversarial Neural Architecture Search for GANs
• EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs
• Coarse-to-Fine Searching for Efficient Generative Adversarial Networks
• Dynamically Grown Generative Adversarial Networks