Learning Disentangled Representations with Semi-Supervised Deep Generative Models

NeurIPS 2017 N. SiddharthBrooks PaigeJan-Willem van de MeentAlban DesmaisonNoah D. GoodmanPushmeet KohliFrank WoodPhilip H. S. Torr

Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable... (read more)

PDF Abstract

Evaluation results from the paper

  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.