Poster
Learning Disentangled Joint Continuous and Discrete Representations
Emilien Dupont
Room 517 AB #151
Keywords: [ Variational Inference ] [ Unsupervised Learning ] [ Deep Autoencoders ] [ Generative Models ] [ Representation Learning ]
We present a framework for learning disentangled and interpretable jointly continuous and discrete representations in an unsupervised manner. By augmenting the continuous latent distribution of variational autoencoders with a relaxed discrete distribution and controlling the amount of information encoded in each latent unit, we show how continuous and categorical factors of variation can be discovered automatically from data. Experiments show that the framework disentangles continuous and discrete generative factors on various datasets and outperforms current disentangling methods when a discrete generative factor is prominent.
Live content is unavailable. Log in and register to view live content