45 citations · 126 across the 10 of their papers we have counts for
3 papers · 1 filter
HiLLoC: Lossless Image Compression with Hierarchical Latent Variable Models
James Townsend, Thomas Bird, Julius Kunze +1
We make the following striking observation: fully convolutional VAE models trained on 32x32 ImageNet can generalize well, not just to 64x64 but also to far larger photographs, with…
Gaussian Mean Field Regularizes by Limiting Learned Information
Julius Kunze, Louis Kirsch, Hippolyt Ritter +1
Variational inference with a factorized Gaussian posterior estimate is a widely used approach for learning parameters and hidden variables. Empirically, a regularizing effect can b…
Practical Lossless Compression with Latent Variables using Bits Back Coding
James Townsend, Tom Bird, David Barber
Deep latent variable models have seen recent success in many data domains. Lossless compression is an application of these models which, despite having the potential to be highly u…