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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition s. 6848 - 6856
Hlavní autoři: Zhang, Xiangyu, Zhou, Xinyu, Lin, Mengxiao, Sun, Jian
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2018
Témata:
Complexity theory
Computational modeling
Computer architecture
Convolution
Mobile handsets
Neural networks
Task analysis
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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