Skip to content
CaMLSysUniversity of Cambridge
Home People Publications Projects Contact

← All publications

COIN++: Neural Compression Across Modalities

  • Emilien DupontUniversity of Oxford
  • Hrushikesh LoyaUniversity of Oxford
  • Milad AlizadehUniversity of Oxford
  • Adam GolińskiUniversity of Oxford
  • Yee Whye TehUniversity of Oxford
  • Arnaud DoucetUniversity of Oxford

Transactions on Machine Learning Research (TMLR), 2022

Abstract

Neural compression algorithms are typically based on autoencoders that require specialized encoder and decoder architectures for different data modalities. In this paper, we propose COIN++, a neural compression framework that seamlessly handles a wide range of data modalities. Our approach is based on converting data to implicit neural representations, i.e. neural functions that map coordinates (such as pixel locations) to features (such as RGB values). Then, instead of storing the weights of the implicit neural representation directly, we store modulations applied to a meta-learned base network as a compressed code for the data. We further quantize and entropy code these modulations, leading to large compression gains while reducing encoding time by two orders of magnitude compared to baselines. We empirically demonstrate the feasibility of our method by compressing various data modalities, from images and audio to medical and climate data.

Materials

  • PDF
BibTeX
@article{dupont2022coin,
  title = {{COIN++: Neural Compression Across Modalities}},
  author = {Dupont, Emilien and Loya, Hrushikesh and Alizadeh, Milad and Goliński, Adam and Teh, Yee Whye and Doucet, Arnaud},
  year = {2022},
  journal = {Transactions on Machine Learning Research (TMLR)},
  url = {https://openreview.net/forum?id=NXB0rEM2Tq}
}
Cambridge Machine Learning Systems Group
Department of Computer Science and Technology
University of Cambridge
ContactGitHub