ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

TLDR

ShuffleNet is a highly computation‑efficient CNN architecture designed for mobile devices with limited computing power. ShuffleNet reduces computation cost by using pointwise group convolutions and channel‑shuffle operations while preserving accuracy. On ImageNet and MS COCO, ShuffleNet achieves lower top‑1 error than MobileNet under 40 MFLOPs and delivers about 13× speedup over AlexNet on ARM devices with comparable accuracy.

Abstract

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 on ImageNet classification task, under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves ~13x actual speedup over AlexNet while maintaining comparable accuracy.