Learning Discriminative Latent Attributes for Zero-Shot Classification

doi:10.1109/ICCV.2017.453

	Learning Discriminative Latent Attributes for Zero-Shot Classification
	Jiang, Huajie1,2,3 ; Wang, Ruiping 1; Shan, Shiguang 1; Yang, Yi 4; Chen, Xilin1
	2017
会议录名称	2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
ISSN	2380-7504
卷号	2017-October
页码	4233-4242
发表状态	已发表
DOI	10.1109/ICCV.2017.453
摘要	Zero-shot learning (ZSL) aims to transfer knowledge from observed classes to the unseen classes, based on the assumption that both the seen and unseen classes share a common semantic space, among which attributes enjoy a great popularity. However, few works study whether the human-designed semantic attributes are discriminative enough to recognize different classes. Moreover, attributes are often correlated with each other, which makes it less desirable to learn each attribute independently. In this paper, we propose to learn a latent attribute space, which is not only discriminative but also semantic-preserving, to perform the ZSL task. Specifically, a dictionary learning framework is exploited to connect the latent attribute space with attribute space and similarity space. Extensive experiments on four benchmark datasets show the effectiveness of the proposed approach.
出版地	345 E 47TH ST, NEW YORK, NY 10017 USA
会议地点	Venice, Italy
会议日期	22-29 Oct. 2017
URL	查看原文
收录类别	CPCI ; EI
语种	英语
资助项目	Youth Innovation Promotion Association CAS[2015085]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000425498404032
出版者	IEEE
EI入藏号	20180704804206
EI主题词	Semantics
EI分类号	Computer Applications:723.5
WOS关键词	OBJECT CLASSES
原始文献类型	Proceedings Paper
来源库	IEEE
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/16304
专题	信息科学与技术学院信息科学与技术学院_特聘教授组_陈熙霖组信息科学与技术学院_博士生
通讯作者	Jiang, Huajie
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Shanghai Inst Microsyst & Informat Technol, Shanghai 200050, Peoples R China 3.ShanghaiTech Univ, Shanghai 200031, Peoples R China 4.Huawei Technol Co Ltd, Beijing 100085, Peoples R China
第一作者单位	上海科技大学
通讯作者单位	上海科技大学
推荐引用方式 GB/T 7714	Jiang, Huajie,Wang, Ruiping,Shan, Shiguang,et al. Learning Discriminative Latent Attributes for Zero-Shot Classification[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2017:4233-4242.