ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

被引：5963

作者：

Zhang, Xiangyu ^{[1
]}

Zhou, Xinyu ^{[1
]}

Lin, Mengxiao ^{[1
]}

Sun, Ran ^{[1
]}

机构：

[1] Megvii Inc Face, Beijing, Peoples R China

来源：

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2018年

关键词：

D O I：

10.1109/CVPR.2018.00716

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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- i error (absolute 7.8%) than recent MobileNet [] on ImageNet classification task, under the computation budget of 40 MFLOPs. On an ARM- based mobile device, ShuffleNet achieves similar to 13x actual speedup over AlexNet while maintaining comparable accuracy.

引用

页码：6848 / 6856

页数：9