中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 智能制造技术与系统研究中心
  5. 多维数据分析团队
CNQ: Compressor-Based Non-uniform Quantization of Deep Neural NetworksInspec keywordsOther keywordsKey words

文献类型：期刊论文

作者Yuan, Yong1,3; Chen, Chen1,3; Hu, Xiyuan4; Peng, Silong1,2,3
刊名CHINESE JOURNAL OF ELECTRONICS
出版日期2020-11-01
卷号29期号:6页码:1126-1133
关键词entropy image classification learning (artificial intelligence) neural nets object detection optimisation quantisation (signal) network structure DNN low-bit quantization time-consuming training compressor-based fast nonuniform quantization method quantization model post-training quantization methods deep neural networks network quantization compressor-based nonuniform quantization CNQ Non-uniform quantization Knowledge distillation Unlabeled samples Network compression
ISSN号1022-4653
DOI10.1049/cje.2020.09.014
通讯作者Chen, Chen(chen.chen@ia.ac.cn)
英文摘要Deep neural networks (DNNs) have achieved state-of-the-art performance in a number of domains but suffer intensive complexity. Network quantization can effectively reduce computation and memory costs without changing network structure, facilitating the deployment of DNNs on mobile devices. While the existing methods can obtain good performance, low-bit quantization without time-consuming training or access to the full dataset is still a challenging problem. In this paper, we develop a novel method named Compressorbased non-uniform quantization (CNQ) method to achieve non-uniform quantization of DNNs with few unlabeled samples. Firstly, we present a compressor-based fast nonuniform quantization method, which can accomplish nonuniform quantization without iterations. Secondly, we propose to align the feature maps of the quantization model with the pre-trained model for accuracy recovery. Considering the property difference between different activation channels, we utilize the weighted-entropy perchannel to optimize the alignment loss. In the experiments, we evaluate the proposed method on image classification and object detection. Our results outperform the existing post-training quantization methods, which demonstrate the effectiveness of the proposed method.
资助项目National Natural Science Foundation of China[61906194] ; National Natural Science Foundation of China[61571438]
WOS研究方向Engineering
语种英语
WOS记录号WOS:000609935600016
出版者TECHNOLOGY EXCHANGE LIMITED HONG KONG
资助机构National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/42894]  
专题自动化研究所_智能制造技术与系统研究中心_多维数据分析团队
通讯作者Chen, Chen
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Beijing Visyst Co Ltd, Beijing 100083, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
4.Nanjing Univ Sci & Technol, Sch Comp Sci & Engn, Nanjing 210094, Peoples R China
推荐引用方式
GB/T 7714		 Yuan, Yong,Chen, Chen,Hu, Xiyuan,et al. CNQ: Compressor-Based Non-uniform Quantization of Deep Neural NetworksInspec keywordsOther keywordsKey words[J]. CHINESE JOURNAL OF ELECTRONICS,2020,29(6):1126-1133.
APA Yuan, Yong,Chen, Chen,Hu, Xiyuan,&Peng, Silong.(2020).CNQ: Compressor-Based Non-uniform Quantization of Deep Neural NetworksInspec keywordsOther keywordsKey words.CHINESE JOURNAL OF ELECTRONICS,29(6),1126-1133.
MLA Yuan, Yong,et al."CNQ: Compressor-Based Non-uniform Quantization of Deep Neural NetworksInspec keywordsOther keywordsKey words".CHINESE JOURNAL OF ELECTRONICS 29.6(2020):1126-1133.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。