AdversarialNAS: Adversarial Neural Architecture Search for GANs

Abstract

Neural Architecture Search (NAS) that aims to automate the procedure of architecture design has achieved promising results in many computer vision fields. In this paper, we propose an AdversarialNAS method specially tailored for Generative Adversarial Networks (GANs) to search for a superior generative model on the task of unconditional image generation. The proposed method leverages an adversarial searching mechanism to search for the architectures of generator and discriminator simultaneously in a differentiable manner. Therefore, the searching algorithm considers the relevance and balance between the two networks leading to search for a superior generative model. Besides, AdversarialNAS does not need any extra evaluation metric to evaluate the performance of the architecture in each searching iteration, which is very efficient and can take only 1 GPU day to search for an optimal network architecture in a large search space (10 38 ). Experiments demonstrate the effectiveness and superiority of our method. The discovered generative model sets a new state-of-the-art FID score of 10.87 and highly competitive Inception Score of 8.74 on CIFAR-10. Its transferability is also proven by setting new state-of-the-art FID score of 26.98 and Inception score of 9.63 on STL-10. Our code will be released to facilitate the related academic and industrial study.

Searching towards Class-Aware Generators for Conditional Generative Adversarial Networks

“…We perform experiments on some popular benchmarks, including the CIFAR10 and CIFAR100 datasets that have different numbers of classes. For unconditional image generation, our search method shows superior performance, comparable to those equipped with the automatic search [13,11,38]. For class-conditional image generation, our approach shows significant gains in terms of important criteria (e.g., FID and intra FIDs).…”

“…There are a number of improvements for the original GAN, e.g., changing the objective function [1,15,27,18,33], improving network architecture [34,3,21,9,42,19], using multiple generators or discriminators [37,17,2,10,12,30]. Recently, the surge in neural architecture search (NAS) has triggered a wave of interest in automatically designing the network architecture of GAN [38,13,11].…”

WAS-VTON: Warping Architecture Search for Virtual Try-on Network

“…Neural Architecture Search. Neural Architecture Search (NAS) has been utilized to search the optimal network architecture for numerous computer vision problems, such as image classification [1,17,28,30,41,49], object detection [11,24,35,42,45], image segmentation [29,53], and image synthesis [10,14]. In general, the NAS algorithms need to solve the problems of architecture search and weight optimization.…”

Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search

“…The computational cost for AGAN is comparably very expensive (1200 GPU days). In addition, AdversarialNAS [10] and DEGAS [9] adopted a different approach, i.e., differentiable searching strategy [35], for the GAN architecture search problem.…”