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
  • [41] Patch-wise Mixed-Precision Quantization of Vision Transformer
    Xiao, Junrui
    Li, Zhikai
    Yang, Lianwei
    Gu, Qingyi
    2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [42] Mixed precision quantization of silicon optical neural network chip
    Zhang, Ye
    Wang, Ruiting
    Zhang, Yejin
    Pan, Jiaoqing
    OPTICS COMMUNICATIONS, 2025, 574
  • [43] DC-MPQ: Distributional Clipping-based Mixed-Precision Quantization for Convolutional Neural Networks
    Lee, Seungjin
    Kim, Hyun
    2022 IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE CIRCUITS AND SYSTEMS (AICAS 2022): INTELLIGENT TECHNOLOGY IN THE POST-PANDEMIC ERA, 2022, : 130 - 133
  • [44] Deep Neural Network Compression Method Based on Product Quantization
    Fang, Xiuqin
    Liu, Han
    Xie, Guo
    Zhang, Youmin
    Liu, Ding
    PROCEEDINGS OF THE 39TH CHINESE CONTROL CONFERENCE, 2020, : 7035 - 7040
  • [45] A Dynamic Execution Neural Network Processor for Fine-Grained Mixed-Precision Model Training Based on Online Quantization Sensitivity Analysis
    Liu, Ruoyang
    Wei, Chenhan
    Yang, Yixiong
    Wang, Wenxun
    Yuan, Binbin
    Yang, Huazhong
    Liu, Yongpan
    IEEE JOURNAL OF SOLID-STATE CIRCUITS, 2024, 59 (09) : 3082 - 3093
  • [46] A Mixed-Precision Quantization Method without Accuracy Degradation Using Semilayers
    Matsumoto, Kengo
    Matsuda, Tomoya
    Inoue, Atsuki
    Kawaguchi, Hiroshi
    Sakai, Yasufumi
    ASIAN CONFERENCE ON MACHINE LEARNING, VOL 222, 2023, 222
  • [47] Campo: Cost-Aware Performance Optimization for Mixed-Precision Neural Network Training
    He, Xin
    Sun, Jianhua
    Chen, Hao
    Li, Dong
    PROCEEDINGS OF THE 2022 USENIX ANNUAL TECHNICAL CONFERENCE, 2022, : 505 - 518
  • [48] Mixed-Precision Quantization of U-Net for Medical Image Segmentation
    Guo, Liming
    Fei, Wen
    Dai, Wenrui
    Li, Chenglin
    Zou, Junni
    Xiong, Hongkai
    2022 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS 22), 2022, : 2871 - 2875
  • [49] Rethinking Differentiable Search for Mixed-Precision Neural Networks
    Cai, Zhaowei
    Vasconcelos, Nuno
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 2346 - 2355
  • [50] Low-latency Buffering for Mixed-precision Neural Network Accelerator with MulTAP and FQPipe
    Li, Yike
    Wang, Zheng
    Ou, Wenhui
    Liang, Chen
    Zhou, Weiyu
    Yang, Yongkui
    Chen, Chao
    2024 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, ISCAS 2024, 2024,
12345