CNQ:Compressor-Based Non-uniform Quantization of Deep Neural Networks

CASIA OpenIR > 智能制造技术与系统研究中心 > 多维数据分析（彭思龙）-技术团队

	CNQ:Compressor-Based Non-uniform Quantization of Deep Neural Networks
	Yuan Yong1 ; Chen Chen1 ; Hu Xiyuan2 ; Peng Silong1
发表期刊	Chinese Journal of Electronics
ISSN	1022-4653
	2020
卷号	29 期号:6 页码:1126-1133
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.
关键词	Non-uniform quantization Knowledge distillation Unlabeled samples Network compression
收录类别	CSCD
语种	英语
CSCD记录号	CSCD:6873930
七大方向——子方向分类	机器学习
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/43071
专题	智能制造技术与系统研究中心_多维数据分析（彭思龙）-技术团队
作者单位	1.中国科学院自动化研究所 2.马来西亚理科大学
第一作者单位	中国科学院自动化研究所
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 Networks[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 Networks.Chinese Journal of Electronics,29(6),1126-1133.
MLA	Yuan Yong,et al."CNQ:Compressor-Based Non-uniform Quantization of Deep Neural Networks".Chinese Journal of Electronics 29.6(2020):1126-1133.