Efficient and Accurate Approximations of Nonlinear Convolutional Networks
Abstract
This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs). Unlike existing methods that are designed for approximating linear filters or linear responses, our method takes the nonlinear units into account. We minimize the reconstruction error of the nonlinear responses, subject to a low-rank constraint which helps to reduce the complexity of filters. We develop an effective solution to this constrained nonlinear optimization problem. An algorithm is also presented for reducing the accumulated error when multiple layers are approximated. A whole-model speedup ratio of 4x is demonstrated on a large network trained for ImageNet, while the top-5 error rate is only increased by 0.9%. Our accelerated model has a comparably fast speed as the "AlexNet", but is 4.7% more accurate.
Cite
Text
Zhang et al. "Efficient and Accurate Approximations of Nonlinear Convolutional Networks." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7298809Markdown
[Zhang et al. "Efficient and Accurate Approximations of Nonlinear Convolutional Networks." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/zhang2015cvpr-efficient/) doi:10.1109/CVPR.2015.7298809BibTeX
@inproceedings{zhang2015cvpr-efficient,
title = {{Efficient and Accurate Approximations of Nonlinear Convolutional Networks}},
author = {Zhang, Xiangyu and Zou, Jianhua and Ming, Xiang and He, Kaiming and Sun, Jian},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2015},
doi = {10.1109/CVPR.2015.7298809},
url = {https://mlanthology.org/cvpr/2015/zhang2015cvpr-efficient/}
}