ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

by   Xiangyu Zhang, et al.
Megvii Technology Limited

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


page 1

page 2

page 3

page 4


Pelee: A Real-Time Object Detection System on Mobile Devices

An increasing need of running Convolutional Neural Network (CNN) models ...

High Performance Depthwise and Pointwise Convolutions on Mobile Devices

Lightweight convolutional neural networks (e.g., MobileNets) are specifi...

Lightweight Residual Densely Connected Convolutional Neural Network

Extremely efficient convolutional neural network architectures are one o...

MobileFaceNets: Efficient CNNs for Accurate Real-time Face Verification on Mobile Devices

In this paper, we present a class of extremely efficient CNN models call...

PICO: Pipeline Inference Framework for Versatile CNNs on Diverse Mobile Devices

Recent researches in artificial intelligence have proposed versatile con...

WaveletNet: Logarithmic Scale Efficient Convolutional Neural Networks for Edge Devices

We present a logarithmic-scale efficient convolutional neural network ar...

RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization

Feature reuse has been a key technique in light-weight convolutional neu...

Code Repositories


Caffe re-implementation of ShuffleNet [STILL UNDER TEST]

view repo

Please sign up or login with your details

Forgot password? Click here to reset