MXQN: Mixed quantization for reducing bit-width of weights and activations in deep convolutional neural networks

Chenglong Huang, Puguang Liu, Liang Fang. MXQN: Mixed quantization for reducing bit-width of weights and activations in deep convolutional neural networks. Appl. Intell., 51(7):4561-4574, 2021. [doi]

@article{HuangLF21-0,
  title = {MXQN: Mixed quantization for reducing bit-width of weights and activations in deep convolutional neural networks},
  author = {Chenglong Huang and Puguang Liu and Liang Fang},
  year = {2021},
  doi = {10.1007/s10489-020-02109-0},
  url = {https://doi.org/10.1007/s10489-020-02109-0},
  researchr = {https://researchr.org/publication/HuangLF21-0},
  cites = {0},
  citedby = {0},
  journal = {Appl. Intell.},
  volume = {51},
  number = {7},
  pages = {4561-4574},
}