Towards Conceptual Compression
Abstract
We introduce convolutional DRAW, a homogeneous deep generative model achieving state-of-the-art performance in latent variable image modeling. The algorithm naturally stratifies information into higher and lower level details, creating abstract features and as such addressing one of the fundamentally desired properties of representation learning. Furthermore, the hierarchical ordering of its latents creates the opportunity to selectively store global information about an image, yielding a high quality 'conceptual compression' framework.
Cite
Text
Gregor et al. "Towards Conceptual Compression." Neural Information Processing Systems, 2016.Markdown
[Gregor et al. "Towards Conceptual Compression." Neural Information Processing Systems, 2016.](https://mlanthology.org/neurips/2016/gregor2016neurips-conceptual/)BibTeX
@inproceedings{gregor2016neurips-conceptual,
title = {{Towards Conceptual Compression}},
author = {Gregor, Karol and Besse, Frederic and Rezende, Danilo Jimenez and Danihelka, Ivo and Wierstra, Daan},
booktitle = {Neural Information Processing Systems},
year = {2016},
pages = {3549-3557},
url = {https://mlanthology.org/neurips/2016/gregor2016neurips-conceptual/}
}