ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

@inproceedings{Zhang2018ShuffleNetAE,
  title={ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices},
  author={Xiangyu Zhang and Xinyu Zhou and Mengxiao Lin and Jian Sun},
  booktitle={CVPR},
  year={2018}
}
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… CONTINUE READING
Highly Influential
This paper has highly influenced 31 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 335 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 1 time over the past 90 days. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 218 extracted citations

336 Citations

010020030020172018
Citations per Year
Semantic Scholar estimates that this publication has 336 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 49 references

Inceptionv4

  • C. Szegedy, S. Ioffe, V. Vanhoucke, A. Alemi
  • inception-resnet and the impact of residual…
  • 2016
Highly Influential
5 Excerpts

Similar Papers

Loading similar papers…