Slimmable Generative Adversarial Networks
Keywords:Neural Generative Models & Autoencoders, Learning on the Edge & Model Compression, Computational Photography, Image & Video Synthesis
AbstractGenerative 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.
How to Cite
Hou, L., Yuan, Z., Huang, L., Shen, H., Cheng, X., & Wang, C. (2021). Slimmable Generative Adversarial Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 35(9), 7746-7753. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16946
AAAI Technical Track on Machine Learning II