English

f-VAEs: Improve VAEs with Conditional Flows

Machine Learning 2018-09-18 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

In this paper, we integrate VAEs and flow-based generative models successfully and get f-VAEs. Compared with VAEs, f-VAEs generate more vivid images, solved the blurred-image problem of VAEs. Compared with flow-based models such as Glow, f-VAE is more lightweight and converges faster, achieving the same performance under smaller-size architecture.

Cite

@article{arxiv.1809.05861,
  title  = {f-VAEs: Improve VAEs with Conditional Flows},
  author = {Jianlin Su and Guang Wu},
  journal= {arXiv preprint arXiv:1809.05861},
  year   = {2018}
}
R2 v1 2026-06-23T04:07:48.158Z