CASIA OpenIR  > 模式识别国家重点实验室  > 多媒体计算
Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation
Li, Jinfeng1; Liu, Weifeng1; Zhou, Yicong2; Yu, Jun3; Tao, Dapeng4; Xu, Changsheng5
发表期刊ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
ISSN1551-6857
2022-08-01
卷号18期号:3页码:18
通讯作者Li, Jinfeng(lijinfeng_stu@163.com)
摘要Domain adaptation aims to generalize a model from a source domain to tackle tasks in a related but different target domain. Traditional domain adaptation algorithms assume that enough labeled data, which are treated as the prior knowledge are available in the source domain. However, these algorithms will be infeasible when only a few labeled data exist in the source domain, thus the performance decreases significantly. To address this challenge, we propose a Domain-invariant Graph Learning (DGL) approach for domain adaptation with only a few labeled source samples. Firstly, DGL introduces the Nystrom method to construct a plastic graph that shares similar geometric property with the target domain. Then, DGL flexibly employs the Nystrom approximation error to measure the divergence between the plastic graph and source graph to formalize the distribution mismatch from the geometric perspective. Through minimizing the approximation error, DGL learns a domain-invariant geometric graph to bridge the source and target domains. Finally, we integrate the learned domain-invariant graph with the semi-supervised learning and further propose an adaptive semi-supervised model to handle the cross-domain problems. The results of extensive experiments on popular datasets verify the superiority of DGL, especially when only a few labeled source samples are available.
关键词Domain adaptation domain-invariant graph the Nystrom method few labeled source samples
DOI10.1145/3487194
关键词[WOS]FRAMEWORK ; FEATURES ; KERNEL ; REGULARIZATION ; MATRIX
收录类别SCI
语种英语
资助项目National Natural Science Foundation of China[61671480] ; National Natural Science Foundation of China[61836002] ; National Natural Science Foundation of China[62020106007] ; Major Scientific and Technological Projects of CNPC[ZD2019-183-008] ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR)[202000009]
项目资助者National Natural Science Foundation of China ; Major Scientific and Technological Projects of CNPC ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR)
WOS研究方向Computer Science
WOS类目Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS记录号WOS:000772650600006
出版者ASSOC COMPUTING MACHINERY
引用统计
被引频次:9[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/48202
专题模式识别国家重点实验室_多媒体计算
通讯作者Li, Jinfeng
作者单位1.Xidian Univ, China Univ Petr East China, State Key Lab Integrated Serv Networks, 66 Changjiang West Rd, Qingdao 266580, Peoples R China
2.Univ Macau, Macau, Peoples R China
3.Hangzhou Dianzi Univ, 1158 2 Dajie, Hangzhou 310018, Peoples R China
4.Yunnan Univ, Kunming 650091, Yunnan, Peoples R China
5.Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Li, Jinfeng,Liu, Weifeng,Zhou, Yicong,et al. Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2022,18(3):18.
APA Li, Jinfeng,Liu, Weifeng,Zhou, Yicong,Yu, Jun,Tao, Dapeng,&Xu, Changsheng.(2022).Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,18(3),18.
MLA Li, Jinfeng,et al."Domain-invariant Graph for Adaptive Semi-supervised Domain Adaptation".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 18.3(2022):18.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Li, Jinfeng]的文章
[Liu, Weifeng]的文章
[Zhou, Yicong]的文章
百度学术
百度学术中相似的文章
[Li, Jinfeng]的文章
[Liu, Weifeng]的文章
[Zhou, Yicong]的文章
必应学术
必应学术中相似的文章
[Li, Jinfeng]的文章
[Liu, Weifeng]的文章
[Zhou, Yicong]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。