Skip to main content

> ML_LITERATURE // ZHANG-2018-SHUFFLENET-EFFICIENT-CONVOLUTIONAL-NEURAL-NETWORK-MOBILE_v1.0

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, Jian Sun · IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

seminal-architecture2018foundationalthirdPartyReproduced
DOI: 10.1109/CVPR.2018.00716Back to Literature

Principal Contribution

Introduced pointwise group convolutions and channel shuffle operations to overcome 1x1 convolution computational bottlenecks, achieving 13x speedup over AlexNet on ARM devices.

Operational Relevance

Serves as qualified reference for deploying task-image-classification in production.

Assumptions

  • Spatial feature coherence and data manifold structure adhere to continuous representation hypotheses

Limitations

  • Computational complexity scales with spatial resolution and parameter capacity

Connected Algorithms, Architectures & Tools

Related Algorithms:
Related Architectures:
Implementing Libraries: