UM  > 科技學院  > 電腦及資訊科學系
A Regularization Approach for Instance-Based Superset Label Learning
Gong, Chen1,2; Liu, Tongliang3; Tang, Yuanyan4,5; Yang, Jian1; Yang, Jie2; Tao, Dacheng6

Different from the traditional supervised learning in which each training example has only one explicit label, superset label learning (SLL) refers to the problem that a training example can be associated with a set of candidate labels, and only one of them is correct. Existing SLL methods are either regularization-based or instance-based, and the latter of which has achieved state-of-the-art performance. This is because the latest instance-based methods contain an explicit disambiguation operation that accurately picks up the groundtruth label of each training example from its ambiguous candidate labels. However, such disambiguation operation does not fully consider the mutually exclusive relationship among different candidate labels, so the disambiguated labels are usually generated in a nondiscriminative way, which is unfavorable for the instance-based methods to obtain satisfactory performance. To address this defect, we develop a novel regularization approach for instance-based superset label (RegISL) learning so that our instance-based method also inherits the good discriminative ability possessed by the regularization scheme. Specifically, we employ a graph to represent the training set, and require the examples that are adjacent on the graph to obtain similar labels. More importantly, a discrimination term is proposed to enlarge the gap of values between possible labels and unlikely labels for every training example. As a result, the intrinsic constraints among different candidate labels are deployed, and the disambiguated labels generated by RegISL are more discriminative and accurate than those output by existing instance-based algorithms. The experimental results on various tasks convincingly demonstrate the superiority of our RegISL to other typical SLL methods in terms of both training accuracy and test accuracy.

KeywordConcave Convex Procedure (Cccp) Disambiguation Regularization Superset Label Learning (Sll)
URLView the original
Indexed BySCI
WOS Research AreaAutomation & Control Systems ; Computer Science
WOS SubjectAutomation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS IDWOS:000424826800012
The Source to ArticleWOS
Fulltext Access
Citation statistics
Cited Times [WOS]:22   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
Corresponding AuthorGong, Chen; Liu, Tongliang; Tang, Yuanyan; Yang, Jian; Yang, Jie; Tao, Dacheng
Affiliation1.School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
2.Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai 200240, China
3.School of Software, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia
4.Faculty of Science and Technology, University of Macau, Macau 999078, China
5.College of Computer Science, Chongqing University, Chongqing 400000, China
6.School of Information Technologies and the Faculty of Engineering and Information Technologies, University of Sydney, Sydney, NSW 2008, Australia
Corresponding Author AffilicationFaculty of Science and Technology
Recommended Citation
GB/T 7714
Gong, Chen,Liu, Tongliang,Tang, Yuanyan,et al. A Regularization Approach for Instance-Based Superset Label Learning[J]. IEEE TRANSACTIONS ON CYBERNETICS,2018,48(3):967-978.
APA Gong, Chen,Liu, Tongliang,Tang, Yuanyan,Yang, Jian,Yang, Jie,&Tao, Dacheng.(2018).A Regularization Approach for Instance-Based Superset Label Learning.IEEE TRANSACTIONS ON CYBERNETICS,48(3),967-978.
MLA Gong, Chen,et al."A Regularization Approach for Instance-Based Superset Label Learning".IEEE TRANSACTIONS ON CYBERNETICS 48.3(2018):967-978.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Gong, Chen]'s Articles
[Liu, Tongliang]'s Articles
[Tang, Yuanyan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Gong, Chen]'s Articles
[Liu, Tongliang]'s Articles
[Tang, Yuanyan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Gong, Chen]'s Articles
[Liu, Tongliang]'s Articles
[Tang, Yuanyan]'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.