Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
Machine Learning
2017-06-09 v2 Computer Vision and Pattern Recognition
Abstract
We present a new approach to learn compressible representations in deep architectures with an end-to-end training strategy. Our method is based on a soft (continuous) relaxation of quantization and entropy, which we anneal to their discrete counterparts throughout training. We showcase this method for two challenging applications: Image compression and neural network compression. While these tasks have typically been approached with different methods, our soft-to-hard quantization approach gives results competitive with the state-of-the-art for both.
Cite
@article{arxiv.1704.00648,
title = {Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations},
author = {Eirikur Agustsson and Fabian Mentzer and Michael Tschannen and Lukas Cavigelli and Radu Timofte and Luca Benini and Luc Van Gool},
journal= {arXiv preprint arXiv:1704.00648},
year = {2017}
}