ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two new operations, pointwise group convolution and channel shuffle, to greatly red...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 6848 - 6856
Main Authors Zhang, Xiangyu, Zhou, Xinyu, Lin, Mengxiao, Sun, Jian
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Complexity theory
Computational modeling
Computer architecture
Convolution
Mobile handsets
Neural networks
Task analysis
Online AccessGet full text

Cover

More Information
Summary:We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two new operations, pointwise group convolution and channel shuffle, to greatly reduce computation cost while maintaining accuracy. Experiments on ImageNet classification and MS COCO object detection demonstrate the superior performance of ShuffleNet over other structures, e.g. lower top-1 error (absolute 7.8%) than recent MobileNet [12] on ImageNet classification task, under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves ~13Ã- actual speedup over AlexNet while maintaining comparable accuracy.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00716