AutoGAN: Neural Architecture Search for Generative Adversarial Networks

TL;DR

AutoGAN introduces a neural architecture search method tailored for GANs, automatically discovering generator architectures that outperform many existing models in image generation tasks.

Contribution

This paper pioneers the application of NAS to GANs, proposing a search space, controller, and multi-level strategy for automatic architecture discovery.

Findings

AutoGAN achieves state-of-the-art FID scores on CIFAR-10 and STL-10.

Discovered architectures outperform many hand-crafted GANs.

The method accelerates NAS for GANs using parameter sharing and dynamic resetting.

Abstract

Neural architecture search (NAS) has witnessed prevailing success in image classification and (very recently) segmentation tasks. In this paper, we present the first preliminary study on introducing the NAS algorithm to generative adversarial networks (GANs), dubbed AutoGAN. The marriage of NAS and GANs faces its unique challenges. We define the search space for the generator architectural variations and use an RNN controller to guide the search, with parameter sharing and dynamic-resetting to accelerate the process. Inception score is adopted as the reward, and a multi-level search strategy is introduced to perform NAS in a progressive way. Experiments validate the effectiveness of AutoGAN on the task of unconditional image generation. Specifically, our discovered architectures achieve highly competitive performance compared to current state-of-the-art hand-crafted GANs, e.g., setting new state-of-the-art FID scores of 12.42 on CIFAR-10, and 31.01 on STL-10, respectively. We also conclude with a discussion of the current limitations and future potential of AutoGAN. The code is available at https://github.com/TAMU-VITA/AutoGAN