CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Accelerating Convolutional Neural Networks for Mobile Applications
Wang, Peisong1,2; Cheng, Jian1,2,3
2016
Conference NameACM International Conference on Multimedia
Pages541-545
Conference Date2016.10-15-10.19
Conference PlaceAmsterdam, Netherlands
Abstract

Convolutional neural networks (CNNs) have achieved remarkable performance in a wide range of computer vision tasks, typically at the cost of massive computational complexity. The low speed of these networks may hinder real-time applications especially when computational resources are limited. In this paper, an efficient and effective approach is proposed to accelerate the test-phase computation of CNNs based on low-rank and group sparse tensor decomposition. Specifically, for each convolutional layer, the kernel tensor is decomposed into the sum of a small number of low multilinear rank tensors. Then we replace the original kernel tensors in all layers with the approximate tensors and fine-tune the whole net with respect to the final classification task using standard backpropagation.

Comprehensive experiments on ILSVRC-12 demonstrate significant reduction in computational complexity, at the cost of negligible loss in accuracy. For the widely used VGG-16 model, our approach obtains a 6.6 times speed-up on PC and 5.91 times speed up on mobile device of the whole network with less than 1% increase on top-5 error.


KeywordConvolutional Neural Networks Acceleration Image Classification Tensor Decomposition
Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/20148
Collection模式识别国家重点实验室_图像与视频分析
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.Center for Excellence in Brain Science and Intelligence Technology
Recommended Citation
GB/T 7714
Wang, Peisong,Cheng, Jian. Accelerating Convolutional Neural Networks for Mobile Applications[C],2016:541-545.
Files in This Item: Download All
File Name/Size DocType Version Access License
Accelerating Convolu(563KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Peisong]'s Articles
[Cheng, Jian]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Peisong]'s Articles
[Cheng, Jian]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Peisong]'s Articles
[Cheng, Jian]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Accelerating Convolutional Neural Networks for Mobile Applications.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.