Transferable contrastive network for generalized zero-shot learning

doi:10.1109/ICCV.2019.00986

	Transferable contrastive network for generalized zero-shot learning
	Jiang, Huajie1,2,3,4 ; Wang, Ruiping 1,2; Shan, Shiguang 1,2; Chen, Xilin1,2
	2019
会议录名称	17TH IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV 2019
ISSN	1550-5499
卷号	2019-October
页码	9764-9773
发表状态	已发表
DOI	10.1109/ICCV.2019.00986
摘要	Zero-shot learning (ZSL) is a challenging problem that aims to recognize the target categories without seen data, where semantic information is leveraged to transfer knowledge from some source classes. Although ZSL has made great progress in recent years, most existing approaches are easy to overfit the sources classes in generalized zero-shot learning (GZSL) task, which indicates that they learn little knowledge about target classes. To tackle such problem, we propose a novel Transferable Contrastive Network (TCN) that explicitly transfers knowledge from the source classes to the target classes. It automatically contrasts one image with different classes to judge whether they are consistent or not. By exploiting the class similarities to make knowledge transfer from source images to similar target classes, our approach is more robust to recognize the target images. Experiments on five benchmark datasets show the superiority of our approach for GZSL. © 2019 IEEE.
会议地点	Seoul, Korea, Republic of
会议日期	27 Oct.-2 Nov. 2019
URL	查看原文
收录类别	EI ; CPCI-S ; CPCI
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20201208326828
EI主题词	Computer vision ; Knowledge management ; Semantics
EI分类号	Computer Applications:723.5
原始文献类型	Conference article (CA)
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/120820
专题	信息科学与技术学院_博士生信息科学与技术学院_特聘教授组_陈熙霖组
通讯作者	Jiang, Huajie
作者单位	1.Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing; 100190, China 2.University of Chinese Academy of Sciences, Beijing; 100049, China 3.Shanghai Institute of Microsystem and Information Technology, CAS, Shanghai; 200050, China 4.School of Information Science and Technology, ShanghaiTech University, Shanghai; 200031, China
第一作者单位	信息科学与技术学院
通讯作者单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Jiang, Huajie,Wang, Ruiping,Shan, Shiguang,et al. Transferable contrastive network for generalized zero-shot learning[C]:Institute of Electrical and Electronics Engineers Inc.,2019:9764-9773.