Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder-Reference-Cited by-同舟云学术

Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder

Author:

Chadebec Clement¹^ORCID,Thibeau-Sutre Elina²,Burgos Ninon²,Allassonniere Stephanie¹

Affiliation:

1. Université de Paris, INRIA, Centre de Recherche des Cordeliers, INSERM, Sorbonne Université, Paris, France

2. Institut du Cerveau - Paris Brain Institute, ICM, Inserm U 1127, CNRS UMR 7225, Inria Aramis project-team, Sorbonne Université, Paris, France

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software

Link

Reference120 articles.

1. Ladder variational autoencoder;sønderby;Proc 29th Annu Conf Neural Inf Process Syst,2016

2. VAE with a vampprior;tomczak;Proc Int Conf Artif Intell Statist,2018

3. Variational lossy autoencoder;chen,2016

4. Learning hierarchical priors in VAEs;klushyn;Proc Adv Neural Inf Process Syst,2019

5. ELBO surgery: Yet another way to carve up the variational evidence lower bound;hoffman;Proc Workshop Adv Approx Bayesian Inference NIPS,2016

Cited by 30 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献