AutoGAN: Neural Architecture Search for Generative Adversarial Networks

08/11/2019
by   Xinyu Gong, et al.
10

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

READ FULL TEXT

page 6

page 7

research
12/04/2019

AdversarialNAS: Adversarial Neural Architecture Search for GANs

Neural Architecture Search (NAS) that aims to automate the procedure of ...
research
02/14/2021

TransGAN: Two Transformers Can Make One Strong GAN

The recent explosive interest on transformers has suggested their potent...
research
02/22/2021

Sandwich Batch Normalization

We present Sandwich Batch Normalization (SaBN), an embarrassingly easy i...
research
04/21/2023

Can GPT-4 Perform Neural Architecture Search?

We investigate the potential of GPT-4~\cite{gpt4} to perform Neural Arch...
research
06/25/2020

Searching towards Class-Aware Generators for Conditional Generative Adversarial Networks

Conditional Generative Adversarial Networks (cGAN) were designed to gene...
research
04/19/2021

Coarse-to-Fine Searching for Efficient Generative Adversarial Networks

This paper studies the neural architecture search (NAS) problem for deve...
research
03/19/2020

GAN Compression: Efficient Architectures for Interactive Conditional GANs

Conditional Generative Adversarial Networks (cGANs) have enabled control...

Please sign up or login with your details

Forgot password? Click here to reset