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. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Transfer channel pruning for compressing deep domain adaptation models

文献类型：期刊论文

作者Yu, Chaohui2,3; Wang, Jindong1; Chen, Yiqiang2,3; Qin, Xin2,3
刊名INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
出版日期2019-11-01
卷号10期号:11页码:3129-3144
关键词Unsupervised domain adaptation Transfer channel pruning Accelerating
ISSN号1868-8071
DOI10.1007/s13042-019-01004-6
英文摘要Deep unsupervised domain adaptation has recently received increasing attention from researchers. However, existing methods are computationally intensive due to the computational cost of convolutional neural networks (CNN) adopted by most work. There is no effective network compression method for such problem. In this paper, we propose a unified transfer channel pruning (TCP) method for accelerating deep unsupervised domain adaptation (UDA) models. TCP method is capable of compressing the deep UDA model by pruning less important channels while simultaneously learning transferable features by reducing the cross-domain distribution divergence. Therefore, it reduces the impact of negative transfer and maintains competitive performance on the target task. To the best of our knowledge, TCP method is the first approach that aims at accelerating deep unsupervised domain adaptation models. TCP method is validated on two main kinds of UDA methods: the discrepancy-based methods and the adversarial-based methods. In addition, it is validated on two benchmark datasets: Office-31 and ImageCLEF-DA with two common backbone networks - VGG16 and ResNet50. Experimental results demonstrate that our TCP method achieves comparable or better classification accuracy than other comparison methods while significantly reducing the computational cost. To be more specific, in VGG16, we get even higher accuracy after pruning 26% floating point operations (FLOPs); in ResNet50, we also get higher accuracy on half of the tasks after pruning 12% FLOPs for both discrepancy-based methods and adversarial-based methods.
资助项目National Key Research & Development Plan of China[2017YFB1002802] ; NSFC[61572471] ; Beijing Municipal Science & Technology Commission[Z171100000117017]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000494802500010
出版者SPRINGER HEIDELBERG
源URL[http://119.78.100.204/handle/2XEOYT63/14838]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Chen, Yiqiang
作者单位1.Microsoft Res Asia, Beijing, Peoples R China
2.Chinese Acad Sci, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing, Peoples R China
3.Univ Chinese Acad Sci, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Yu, Chaohui,Wang, Jindong,Chen, Yiqiang,et al. Transfer channel pruning for compressing deep domain adaptation models[J]. INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS,2019,10(11):3129-3144.
APA Yu, Chaohui,Wang, Jindong,Chen, Yiqiang,&Qin, Xin.(2019).Transfer channel pruning for compressing deep domain adaptation models.INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS,10(11),3129-3144.
MLA Yu, Chaohui,et al."Transfer channel pruning for compressing deep domain adaptation models".INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 10.11(2019):3129-3144.

入库方式： OAI收割

来源：计算技术研究所

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。