NeurIPS 2016poster298 citations
Towards Conceptual Compression
Karol Gregor, Frederic Besse, Danilo Jimenez Rezende, Ivo Danihelka, Daan Wierstra
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.
BibTeX
@inproceedings{NIPS2016_4abe17a1,
author = {Gregor, Karol and Besse, Frederic and Jimenez Rezende, Danilo and Danihelka, Ivo and Wierstra, Daan},
booktitle = {Advances in Neural Information Processing Systems},
editor = {D. Lee and M. Sugiyama and U. Luxburg and I. Guyon and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Towards Conceptual Compression},
url = {https://proceedings.neurips.cc/paper_files/paper/2016/file/4abe17a1c80cbdd2aa241b70840879de-Paper.pdf},
volume = {29},
year = {2016}
}