GADE: a generative adversarial approach to density estimation and its applications

DOI10.1007/S11263-020-01360-9zbMath1483.68332OpenAlexW3064938383MaRDI QIDQ2056114

M. Ehsan Abbasnejad, Javen Shi, Lingqiao Liu, Anton van den Hengel

Publication date: 1 December 2021

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11263-020-01360-9

zbMATH Keywords

generative modelsdeep learningGANflow-based generative models

Mathematics Subject Classification ID

Density estimation (62G07) Artificial neural networks and deep learning (68T07)

Uses Software

• CIFAR
• NICE
• MS-COCO
• PixelCNN++
• TORCS
• Flow-GAN
• Wasserstein GAN
• StackGAN
• InfoGAN
• f-GAN

Cites Work

• Unnamed Item
• Likelihood-free inference via classification
• Convergence rate of linear two-time-scale stochastic approximation.
• A randomized algorithm for approximating the log determinant of a symmetric positive definite matrix
• An Efficient Learning Procedure for Deep Boltzmann Machines
• The Change-of-Variables Formula Using Matrix Volume

This page was built for publication: GADE: a generative adversarial approach to density estimation and its applications