Spatial Broadcast Decoder: A Simple Architecture for Disentangled Representations in VAEs

no code implementations • ICLR Workshop LLD 2019 • Nick Watters, Loic Matthey, Chris P. Burgess, Alexander Lerchner

We present a neural rendering architecture that helps variational autoencoders (VAEs) learn disentangled representations.

Neural Rendering

Multi-Object Representation Learning with Iterative Variational Inference

6 code implementations • 1 Mar 2019 • Klaus Greff, Raphaël Lopez Kaufman, Rishabh Kabra, Nick Watters, Chris Burgess, Daniel Zoran, Loic Matthey, Matthew Botvinick, Alexander Lerchner

Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities.

Object Representation Learning +3

Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies

1 code implementation • NeurIPS 2018 • Alessandro Achille, Tom Eccles, Loic Matthey, Christopher P. Burgess, Nick Watters, Alexander Lerchner, Irina Higgins

Intelligent behaviour in the real-world requires the ability to acquire new knowledge from an ongoing sequence of experiences while preserving and reusing past knowledge.

Representation Learning

Understanding disentangling in $β$-VAE

23 code implementations • 10 Apr 2018 • Christopher P. Burgess, Irina Higgins, Arka Pal, Loic Matthey, Nick Watters, Guillaume Desjardins, Alexander Lerchner

We present new intuitions and theoretical assessments of the emergence of disentangled representation in variational autoencoders.