ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

• Published in: 2018 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
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Complexity theory; Computational modeling; Computer architecture; Convolution; Mobile handsets; Neural networks; Task analysis

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...