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
热门
Deep Subdomain Adaptation Network for Image Classification

文献类型：期刊论文

作者Zhu, Yongchun1,2; Zhuang, Fuzhen1,2; Wang, Jindong3; Ke, Guolin3; Chen, Jingwu; Bian, Jiang3; Xiong, Hui4; He, Qing1,2
刊名IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
出版日期2021-04-01
卷号32期号:4页码:1713-1722
ISSN号2162-237X
关键词Task analysis Adaptation models Kernel Feature extraction Learning systems Semantics Training Domain adaptation fine grained subdomain
DOI10.1109/TNNLS.2020.2988928
英文摘要For a target task where the labeled data are unavailable, domain adaptation can transfer a learner from a different source domain. Previous deep domain adaptation methods mainly learn a global domain shift, i.e., align the global source and target distributions without considering the relationships between two subdomains within the same category of different domains, leading to unsatisfying transfer learning performance without capturing the fine-grained information. Recently, more and more researchers pay attention to subdomain adaptation that focuses on accurately aligning the distributions of the relevant subdomains. However, most of them are adversarial methods that contain several loss functions and converge slowly. Based on this, we present a deep subdomain adaptation network (DSAN) that learns a transfer network by aligning the relevant subdomain distributions of domain-specific layer activations across different domains based on a local maximum mean discrepancy (LMMD). Our DSAN is very simple but effective, which does not need adversarial training and converges fast. The adaptation can be achieved easily with most feedforward network models by extending them with LMMD loss, which can be trained efficiently via backpropagation. Experiments demonstrate that DSAN can achieve remarkable results on both object recognition tasks and digit classification tasks. Our code will be available at https://github.com/easezyc/deep-transfer-learning.
资助项目National Key Research and Development Program of China[2018YFB1004300] ; National Natural Science Foundation of China[U1836206] ; National Natural Science Foundation of China[U1811461] ; National Natural Science Foundation of China[61773361] ; Project of Youth Innovation Promotion Association CAS[2017146]
WOS研究方向Computer Science ; Engineering
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000637534200025
源URL[http://119.78.100.204/handle/2XEOYT63/16672]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhuang, Fuzhen
作者单位1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Microsoft Res, Beijing, Peoples R China
4.Rutgers State Univ, New Brunswick, NJ USA
推荐引用方式
GB/T 7714		 Zhu, Yongchun,Zhuang, Fuzhen,Wang, Jindong,et al. Deep Subdomain Adaptation Network for Image Classification[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2021,32(4):1713-1722.
APA Zhu, Yongchun.,Zhuang, Fuzhen.,Wang, Jindong.,Ke, Guolin.,Chen, Jingwu.,...&He, Qing.(2021).Deep Subdomain Adaptation Network for Image Classification.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,32(4),1713-1722.
MLA Zhu, Yongchun,et al."Deep Subdomain Adaptation Network for Image Classification".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 32.4(2021):1713-1722.

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。