ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

Authors: Zhang, X., Zhou, X., Lin, M., & Sun, J. Year: 2017 Venue: CVPR ArXiv: https://arxiv.org/abs/1707.01083

Summary

ShuffleNet uses channel shuffle to reduce computation while maintaining accuracy. It achieves competitive performance with fewer parameters than MobileNet.

Key Concepts

• Channel shuffle operation
• Group convolutions for efficiency
• Bottleneck architecture
• Faster inference than MobileNet
• Memory-efficient design

Impact

ShuffleNet provided an alternative efficient architecture approach, showing that channel operations could be as effective as spatial operations for efficiency.

Related Papers

• MobileNet: Efficient Networks
• EfficientNet: Model Scaling
• SqueezeNet: Compact Networks

---

Citation:

@inproceedings{zhang2017shufflenet,
  title={ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices},
  author={Zhang, Xiangyu and Zhou, Xinyu and Lin, Mengxiao and Sun, Jian},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
  year={2017}
}