Attribute annotation on large-scale image database by active knowledge transfer

doi:10.1016/j.imavis.2018.06.012

	Attribute annotation on large-scale image database by active knowledge transfer
	Jiang, Huajie1,2,3,4 ; Wang, Ruiping 2,4; Li, Yan 2,4; Liu, Haomiao 2,4; Shan, Shiguang 2,4; Chen, Xilin 2,4
	2018-10
发表期刊	IMAGE AND VISION COMPUTING (IF:4.2[JCR-2023],4.3[5-Year])
ISSN	0262-8856
卷号	78 页码:1-13
发表状态	已发表
DOI	10.1016/j.imavis.2018.06.012
摘要	Attributes are widely used in different vision tasks. However, existing attribute resources are quite limited and most of them are not in large scale. Current attribute annotation process is generally done by human, which is expensive and time-consuming. in this paper, we propose a novel framework to perform effective attribute annotations. Based on the common knowledge that attributes can be shared among different classes, we leverage the benefits of transfer learning and active learning together to transfer knowledge from some existing small attribute databases to large-scale target databases. In order to learn more robust attribute models, attribute relationships are incorporated to assist the learning process. Using the proposed framework, we conduct extensive experiments on two large-scale image databases, i.e. ImageNet and SUN Attribute, where high quality automatic attribute annotations are obtained. (C) 2018 Elsevier B.V. All rights reserved.
关键词	Attribute Annotation Relationship Active learning Transfer learning
收录类别	SCI ; SCIE ; EI
语种	英语
资助项目	Youth Innovation Promotion Association CAS[2015085]
WOS研究方向	Computer Science ; Engineering ; Optics
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic ; Optics
WOS记录号	WOS:000446143900001
出版者	ELSEVIER SCIENCE BV
EI入藏号	20183205666383
EI主题词	Artificial intelligence ; Database systems ; Knowledge management
EI分类号	Computer Software, Data Handling and Applications:723
WOS关键词	FACIAL ATTRIBUTES ; OBJECT CLASSES ; RECOGNITION
原始文献类型	Article
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/28095
专题	信息科学与技术学院_博士生
通讯作者	Wang, Ruiping
作者单位	1.Chinese Acad Sci, Shanghai Inst Microsyst & Informat Technol, Shanghai 200050, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China 4.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
第一作者单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Jiang, Huajie,Wang, Ruiping,Li, Yan,et al. Attribute annotation on large-scale image database by active knowledge transfer[J]. IMAGE AND VISION COMPUTING,2018,78:1-13.
APA	Jiang, Huajie,Wang, Ruiping,Li, Yan,Liu, Haomiao,Shan, Shiguang,&Chen, Xilin.(2018).Attribute annotation on large-scale image database by active knowledge transfer.IMAGE AND VISION COMPUTING,78,1-13.
MLA	Jiang, Huajie,et al."Attribute annotation on large-scale image database by active knowledge transfer".IMAGE AND VISION COMPUTING 78(2018):1-13.