RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisions

Sung-En Chang, Yanyu Li, Mengshu Sun, Weiwen Jiang, Sijia Liu 0001, Yanzhi Wang, Xue Lin. RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisions. In 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021. pages 5231-5240, IEEE, 2021. [doi]

@inproceedings{ChangLSJ0WL21,
  title = {RMSMP: A Novel Deep Neural Network Quantization Framework with Row-wise Mixed Schemes and Multiple Precisions},
  author = {Sung-En Chang and Yanyu Li and Mengshu Sun and Weiwen Jiang and Sijia Liu 0001 and Yanzhi Wang and Xue Lin},
  year = {2021},
  doi = {10.1109/ICCV48922.2021.00520},
  url = {https://doi.org/10.1109/ICCV48922.2021.00520},
  researchr = {https://researchr.org/publication/ChangLSJ0WL21},
  cites = {0},
  citedby = {0},
  pages = {5231-5240},
  booktitle = {2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021},
  publisher = {IEEE},
  isbn = {978-1-6654-2812-5},
}