1.6k citations
- Vi Technology (United States)US5 papers
- Chinese Academy of SciencesCN3 papers
- Hong Kong University of Science and TechnologyHK3 papers
- Tongji UniversityCN3 papers
- Beijing University of Posts and TelecommunicationsCN2 papers
- Chinese University of Hong KongHK2 papers
- Tsinghua UniversityCN2 papers
- University of Science and Technology of ChinaCN2 papers
- Agency for Science, Technology and ResearchSG1 paper
- Australian National UniversityAU1 paper
- Beihang UniversityCN1 paper
- Beijing Institute of TechnologyCN1 paper
Showing 2017 · cs.CVShow all
2 papers · 2 filters
cs.CV2017★ 892 cited
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin +1
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 MF…
cs.CV2017★ 66 cited
Deep Learning with Low Precision by Half-wave Gaussian Quantization
Zhaowei Cai, Xiaodong He, Jian Sun +1
The problem of quantizing the activations of a deep neural network is considered. An examination of the popular binary quantization approach shows that this consists of approximati…