AI Chat AI Image Generator AI Video Text to Speech

f-VAEs: Improve VAEs with Conditional Flows

09/16/2018

∙

by Jianlin Su, et al.

∙

∙

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.

Jianlin Su
21 publications
Guang Wu
2 publications

page 4

page 6

page 7

research

∙ 02/01/2019

Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design

Flow-based generative models are powerful exact likelihood models with e...

97 Jonathan Ho, et al. ∙

research

∙ 06/24/2021

Distilling the Knowledge from Normalizing Flows

Normalizing flows are a powerful class of generative models demonstratin...

0 Dmitry Baranchuk, et al. ∙

research

∙ 05/03/2023

Nonparametric Generative Modeling with Conditional and Locally-Connected Sliced-Wasserstein Flows

Sliced-Wasserstein Flow (SWF) is a promising approach to nonparametric g...

0 Chao Du, et al. ∙

research

∙ 06/07/2021

Generative Flows with Invertible Attentions

Flow-based generative models have shown excellent ability to explicitly ...

1 Rhea Sanjay Sukthanker, et al. ∙

research

∙ 10/07/2021

Flow Plugin Network for conditional generation

Generative models have gained many researchers' attention in the last ye...

0 Patryk Wielopolski, et al. ∙

research

∙ 09/30/2020

RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse prior

Flow-based generative models have become an important class of unsupervi...

7 Hong-Ye Hu, et al. ∙

research

∙ 08/05/2021

Supervised Neural Networks for Illiquid Alternative Asset Cash Flow Forecasting

Institutional investors have been increasing the allocation of the illiq...

0 Tugce Karatas, et al. ∙