most citedAugmenting Variational Autoencoders with Sparse Labels: A Unified Framework for Unsupervised, Semi-(un)supervised, and Supervised Learning

6 citations · 6 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2019★ 6 cited

Augmenting Variational Autoencoders with Sparse Labels: A Unified Framework for Unsupervised, Semi-(un)supervised, and Supervised Learning

Felix Berkhahn, Richard Keys, Wajih Ouertani +2

We present a new flavor of Variational Autoencoder (VAE) that interpolates seamlessly between unsupervised, semi-supervised and fully supervised learning domains. We show that unla…