UM
Zero-Shot Learning with a Partial Set of Observed Attributes
Wang, Yaqing; Kwok, James T.; Yao, Quanming; Ni, Lionel M.; IEEE
2017
Conference Name2017 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
Pages3777-3784
Publication Place345 E 47TH ST, NEW YORK, NY 10017 USA
PublisherIEEE
AbstractAttributes are human-annotated semantic descriptions of label classes. In zero-shot learning (ZSL), they are often used to construct a semantic embedding for knowledge transfer from known classes to new classes. While collecting all attributes for the new classes is criticized as expensive, a subset of these attributes are often easy to acquire. In this paper, we extend ZSL methods to handle this partial set of observed attributes. We first recover the missing attributes through structured matrix completion. We use the low-rank assumption, and leverage properties of the attributes by extracting their rich semantic information from external sources. The resultant optimization problem can be efficiently solved with alternating minimization, in which each of its subproblems has a simple closed-form solution. The predicted attributes can then be used as semantic embeddings in ZSL. Experimental results show that the proposed method outperform existing methods in recovering the structured missing matrix. Moreover, methods using our predicted attributes in ZSL outperforms methods using either the partial set of observed attributes or other semantic embeddings.
URLView the original
Indexed ByCPCI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic
WOS IDWOS:000426968704005
The Source to ArticleWOS
Fulltext Access
Citation statistics
Cited Times [WOS]:2   [WOS Record]     [Related Records in WOS]
Document TypeConference paper
CollectionUniversity of Macau
Recommended Citation
GB/T 7714
Wang, Yaqing,Kwok, James T.,Yao, Quanming,et al. Zero-Shot Learning with a Partial Set of Observed Attributes[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2017:3777-3784.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Yaqing]'s Articles
[Kwok, James T.]'s Articles
[Yao, Quanming]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Yaqing]'s Articles
[Kwok, James T.]'s Articles
[Yao, Quanming]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Yaqing]'s Articles
[Kwok, James T.]'s Articles
[Yao, Quanming]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.