Slimmable Generative Adversarial Networks

by   Liang Hou, et al.

Generative adversarial networks (GANs) have achieved remarkable progress in recent years, but the continuously growing scale of models make them challenging to deploy widely in practical applications. In particular, for real-time generation tasks, different devices require generators of different sizes due to varying computing power. In this paper, we introduce slimmable GANs (SlimGANs), which can flexibly switch the width of the generator to accommodate various quality-efficiency trade-offs at runtime. Specifically, we leverage multiple discriminators that share partial parameters to train the slimmable generator. To facilitate the consistency between generators of different widths, we present a stepwise inplace distillation technique that encourages narrow generators to learn from wide ones. As for class-conditional generation, we propose a sliceable conditional batch normalization that incorporates the label information into different widths. Our methods are validated, both quantitatively and qualitatively, by extensive experiments and a detailed ablation study.


page 3

page 6


Lifelong Twin Generative Adversarial Networks

In this paper, we propose a new continuously learning generative model, ...

Lessons Learned from the Training of GANs on Artificial Datasets

Generative Adversarial Networks (GANs) have made great progress in synth...

StyleWaveGAN: Style-based synthesis of drum sounds with extensive controls using generative adversarial networks

In this paper we introduce StyleWaveGAN, a style-based drum sound genera...

GIU-GANs: Global Information Utilization for Generative Adversarial Networks

In recent years, with the rapid development of artificial intelligence, ...

Toward Spatially Unbiased Generative Models

Recent image generation models show remarkable generation performance. H...

Improved Image Generation via Sparse Modeling

The interest of the deep learning community in image synthesis has grown...

Double Generative Adversarial Networks for Conditional Independence Testing

In this article, we consider the problem of high-dimensional conditional...