Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
Abstract
We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks. These models deliver impressive accuracy, but each image evaluation requires millions of floating point operations, making their deployment on smartphones and Internet-scale clusters problematic. The computation is dominated by the convolution operations in the lower layers of the model. We exploit the redundancy present within the convolutional filters to derive approximations that significantly reduce the required computation. Using large state-of-the-art models, we demonstrate speedups of convolutional layers on both CPU and GPU by a factor of 2×, while keeping the accuracy within 1% of the original model.
Cite
Text
Denton et al. "Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation." Neural Information Processing Systems, 2014.Markdown
[Denton et al. "Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation." Neural Information Processing Systems, 2014.](https://mlanthology.org/neurips/2014/denton2014neurips-exploiting/)BibTeX
@inproceedings{denton2014neurips-exploiting,
title = {{Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation}},
author = {Denton, Emily L and Zaremba, Wojciech and Bruna, Joan and LeCun, Yann and Fergus, Rob},
booktitle = {Neural Information Processing Systems},
year = {2014},
pages = {1269-1277},
url = {https://mlanthology.org/neurips/2014/denton2014neurips-exploiting/}
}