ML Anthology

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun
CVPR 2018
doi:10.1109/CVPR.2018.00716 /cvpr/2018/zhang2018cvpr-shufflenet/

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~cite{howard2017mobilenets} on ImageNet classification task, under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves $sim$13$ imes$ actual speedup over AlexNet while maintaining comparable accuracy.

PDF CVPR Semantic Scholar

Cite

Text

Zhang et al. "ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00716

Markdown

[Zhang et al. "ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/zhang2018cvpr-shufflenet/) doi:10.1109/CVPR.2018.00716

BibTeX

@inproceedings{zhang2018cvpr-shufflenet,
  title     = {{ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices}},
  author    = {Zhang, Xiangyu and Zhou, Xinyu and Lin, Mengxiao and Sun, Jian},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00716},
  url       = {https://mlanthology.org/cvpr/2018/zhang2018cvpr-shufflenet/}
}