Slimmable Generative Adversarial Networks
This work provides a solution for deploying GANs on devices with varying computational power, which is a practical problem for real-time generation applications.
This paper addresses the deployment challenge of large GANs by introducing SlimGANs, which allow the generator's width to be adjusted at runtime to balance quality and efficiency. They achieve this by training a slimmable generator with multiple discriminators and using a stepwise inplace distillation technique to ensure consistency across different generator widths.
Generative adversarial networks (GANs) have achieved remarkable progress in recent years, but the continuously growing scale of models makes 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 \textit{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.