CASIA OpenIR  > 智能制造技术与系统研究中心  > 多维数据分析
Unlabeled Data Driven Channel-Wise Bit-Width Allocation and Quantization Refinement
Yong Yuan1,2; Chen Chen1,2; Xiyuan Hu1,2; Silong Peng1,2,3
2019
Conference NameThe 26th International Conference on Neural Information Processing of the Asia-Pacific Neural Network Society (ICONIP)
Conference Date2019.12.12-15
Conference PlaceSydney, Australia
Abstract

Network quantization can effectively reduce computation and memory costs, facilitating the deployment of complex Deep Neural Networks (DNNs) on mobile equipment. However, the low-bit quantization without time-consuming training or access to the full datasets is still a challenging problem. In this paper, we develop a two-stage quantization method to address these issues, which only requires a few unlabeled samples. Firstly, we present a gradient-based approach to analyze per-channel sensitivity and optimize the bit-width allocation for different channels according to their sensitivity. Secondly, we propose to refine the quantization model by distilling knowledge from the output and intermediate features of the pre-trained model. Extensive experiments on image classification and object detection demonstrate the effectiveness of the proposed method, and it can achieve a promising result in 4-bit quantization.

Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/25818
Collection智能制造技术与系统研究中心_多维数据分析
个人空间
Corresponding AuthorChen Chen
Affiliation1.Institute of Automation, Chinese Academy of Sciences, Beijing, China
2.University of Chinese Academy of Sciences, Beijing, China
3.Beijing ViSystem Corporation Limited, China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Yong Yuan,Chen Chen,Xiyuan Hu,et al. Unlabeled Data Driven Channel-Wise Bit-Width Allocation and Quantization Refinement[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
2019-ICONIP-Unlabele(310KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yong Yuan]'s Articles
[Chen Chen]'s Articles
[Xiyuan Hu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yong Yuan]'s Articles
[Chen Chen]'s Articles
[Xiyuan Hu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yong Yuan]'s Articles
[Chen Chen]'s Articles
[Xiyuan Hu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2019-ICONIP-Unlabeled Data Driven Channel-Wise Bit-Width Allocation and Quantization Refinement.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.