Auxiliary Deep Generative Models

17 Feb 2016Lars MaaløeCasper Kaae SønderbySøren Kaae SønderbyOle Winther

Deep generative models parameterized by neural networks have recently achieved state-of-the-art performance in unsupervised and semi-supervised learning. We extend deep generative models with auxiliary variables which improves the variational approximation... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification SVHN Auxiliary DGN Percentage error 22.86 # 34
Image Classification SVHN Skip DGN Percentage error 16.61 # 32

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet