f-VAEs: Improve VAEs with Conditional Flows
classification
💻 cs.LG
cs.CVstat.ML
keywords
vaesf-vaescomparedflow-basedmodelsachievingarchitectureblurred-image
read the original 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.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.