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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 多媒体计算与图形学团队
Domain-Oriented Semantic Embedding for Zero-Shot Learning

文献类型：期刊论文

作者Min, Shaobo2; Yao, Hantao1; Xie, Hongtao2; Zha, Zheng-Jun2; Zhang, Yongdong2
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2021
卷号23页码:3919-3930
关键词Semantics Visualization Image recognition Image reconstruction Training Gallium nitride Search problems Zero-shot learning multi-modality embedding recognition
ISSN号1520-9210
DOI10.1109/TMM.2020.3033124
通讯作者Xie, Hongtao(htxie@ustc.edu.cn) ; Zhang, Yongdong(zhyd73@ustc.edu.cn)
英文摘要Zero-Shot Learning (ZSL) targets to recognize images from new classes. Existing methods focus on learning a projection function to associate the visual features and category descriptions in the seen domain, which is directly transferred to the unseen domain. However, due to the inherent domain shift, a single shared projection cannot fully capture the domain difference and similarity, thereby making the unseen samples tend to be recognized as seen categories. In this paper, we propose a novel Domain-Oriented Semantic Embedding (DOSE) network that learns specific projections for different domains to better capture the domain characteristics for unbiased ZSL. Besides a domain-shared projection, DOSE learns two auxiliary domain-specific sub-projections to model the semantic-visual association in respective seen and unseen domains. Specifically, the domain-specific projections are learned in a cycle consistency way to capture domain characteristics, and a domain division constraint is developed to penalize the margin between two domain embeddings. Furthermore, to boost semantic-visual association, a semantic-visual dual attention module is designed to automatically remove trivial information in both visual and semantic embeddings under a co-guidance learning manner. Experiments on four public benchmarks prove that the proposed DOSE is robust to the domain shift problem in ZSL and obtains an averaged 5.6% improvement in terms of harmonic mean.
资助项目National Key Research, and Development Program of China[2017YFC0820600] ; National Nature Science Foundation of China[61525206] ; National Nature Science Foundation of China[62022076] ; National Nature Science Foundation of China[U1936210] ; National Postdoctoral Programme for Innovative Talents[BX20180358] ; Youth Innovation Promotion Association Chinese Academy of Sciences[2017209]
WOS研究方向Computer Science ; Telecommunications
语种英语
WOS记录号WOS:000709093100038
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research, and Development Program of China ; National Nature Science Foundation of China ; National Postdoctoral Programme for Innovative Talents ; Youth Innovation Promotion Association Chinese Academy of Sciences
源URL[http://ir.ia.ac.cn/handle/173211/46306]  
专题自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者Xie, Hongtao; Zhang, Yongdong
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China
2.Univ Sci & Technol China, Natl Engn Lab Brain Inspired Intelligence Technol, Hefei 230026, Peoples R China
推荐引用方式
GB/T 7714		 Min, Shaobo,Yao, Hantao,Xie, Hongtao,et al. Domain-Oriented Semantic Embedding for Zero-Shot Learning[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2021,23:3919-3930.
APA Min, Shaobo,Yao, Hantao,Xie, Hongtao,Zha, Zheng-Jun,&Zhang, Yongdong.(2021).Domain-Oriented Semantic Embedding for Zero-Shot Learning.IEEE TRANSACTIONS ON MULTIMEDIA,23,3919-3930.
MLA Min, Shaobo,et al."Domain-Oriented Semantic Embedding for Zero-Shot Learning".IEEE TRANSACTIONS ON MULTIMEDIA 23(2021):3919-3930.

入库方式： OAI收割

来源：自动化研究所

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。