ICLR 2020poster81 citations
HiLLoC: lossless image compression with hierarchical latent variable models
James Townsend, Thomas Bird, Julius Kunze, David Barber
Abstract
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 no changes to the model. We use this property, applying fully convolutional models to lossless compression, demonstrating a method to scale the VAE-based 'Bits-Back with ANS' algorithm for lossless compression to large color photographs, and achieving state of the art for compression of full size ImageNet images. We release Craystack, an open source library for convenient prototyping of lossless compression using probabilistic models, along with full implementations of all of our compression results.
compressionvariational inferencelossless compressiondeep latent variable models
BibTeX
@inproceedings{
Townsend2020HiLLoC:,
title={HiLLoC: lossless image compression with hierarchical latent variable models},
author={James Townsend and Thomas Bird and Julius Kunze and David Barber},
booktitle={International Conference on Learning Representations},
year={2020},
url={https://openreview.net/forum?id=r1lZgyBYwS}
}