Mixed-precision Deep Neural Network Quantization With Multiple Compression Rates

被引：0
|
作者：
Wang, Xuanda [1 ]
Fei, Wen [1 ]
Dai, Wenrui [1 ]
Li, Chenglin [1 ]
Zou, Junni [1 ]
Xiong, Hongkai [1 ]
机构：
[1] Shanghai Jiao Tong Univ, Sch Elect Informat & Elect Engn, Shanghai 200240, Peoples R China
来源：
2023 DATA COMPRESSION CONFERENCE, DCC | 2023年
基金：
中国国家自然科学基金;
关键词：
D O I：
10.1109/DCC55655.2023.00075
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
引用
收藏
页码：371 / 371
页数：1
相关论文
共 50 条
  • [1] Entropy-Driven Mixed-Precision Quantization for Deep Network Design
    Sun, Zhenhong
    Ge, Ce
    Wang, Junyan
    Lin, Ming
    Chen, Hesen
    Li, Hao
    Sun, Xiuyu
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [2] EVOLUTIONARY QUANTIZATION OF NEURAL NETWORKS WITH MIXED-PRECISION
    Liu, Zhenhua
    Zhang, Xinfeng
    Wang, Shanshe
    Ma, Siwei
    Gao, Wen
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 2785 - 2789
  • [3] Joint Optimization of Dimension Reduction and Mixed-Precision Quantization for Activation Compression of Neural Networks
    Tai, Yu-Shan
    Chang, Cheng-Yang
    Teng, Chieh-Fang
    Chen, Yi-Ta
    Wu, An-Yeu
    IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2023, 42 (11) : 4025 - 4037
  • [4] DPQ: dynamic pseudo-mean mixed-precision quantization for pruned neural network
    Pei, Songwen
    Wang, Jiyao
    Zhang, Bingxue
    Qin, Wei
    Xue, Hai
    Ye, Xiaochun
    Chen, Mingsong
    MACHINE LEARNING, 2024, 113 (07) : 4099 - 4112
  • [5] HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision
    Dong, Zhen
    Yao, Zhewei
    Gholami, Amir
    Mahoney, Michael W.
    Keutzer, Kurt
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 293 - 302
  • [6] Mixed-Precision Neural Network Quantization via Learned Layer-Wise Importance
    Tang, Chen
    Ouyang, Kai
    Wang, Zhi
    Zhu, Yifei
    Ji, Wen
    Wang, Yaowei
    Zhu, Wenwu
    COMPUTER VISION, ECCV 2022, PT XI, 2022, 13671 : 259 - 275
  • [7] Joint Pruning and Channel-Wise Mixed-Precision Quantization for Efficient Deep Neural Networks
    Motetti, Beatrice Alessandra
    Risso, Matteo
    Burrello, Alessio
    Macii, Enrico
    Poncino, Massimo
    Pagliari, Daniele Jahier
    IEEE TRANSACTIONS ON COMPUTERS, 2024, 73 (11) : 2619 - 2633
  • [8] Mixed-Precision Network Quantization for Infrared Small Target Segmentation
    Li, Boyang
    Wang, Longguang
    Wang, Yingqian
    Wu, Tianhao
    Lin, Zaiping
    Li, Miao
    An, Wei
    Guo, Yulan
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 12
  • [9] Hardware for Quantized Mixed-Precision Deep Neural Networks
    Rios, Andres
    Nava, Patricia
    PROCEEDINGS OF THE 2022 15TH IEEE DALLAS CIRCUITS AND SYSTEMS CONFERENCE (DCAS 2022), 2022,
  • [10] Deep Neural Network Compression with Single and Multiple Level Quantization
    Xu, Yuhui
    Wang, Yongzhuang
    Zhou, Aojun
    Lin, Weiyao
    Xiong, Hongkai
    THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 4335 - 4342
12345