skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Simple and Effective Complementary Label Learning Based on Mean Square Error Loss

Journal of physics. Conference series, 2023-05, Vol.2504 (1), p.12016 [Peer Reviewed Journal]

Published under licence by IOP Publishing Ltd ;Published under licence by IOP Publishing Ltd. This work is published under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;ISSN: 1742-6588 ;EISSN: 1742-6596 ;DOI: 10.1088/1742-6596/2504/1/012016

Full text available

Citations Cited by
  • Title:
    Simple and Effective Complementary Label Learning Based on Mean Square Error Loss
  • Author: Wang, Chenggang ; Xu, Xiong ; Liu, Defu ; Niu, Xinyu ; Han, Shijiao
  • Subjects: Classifiers ; Deep learning ; Labels ; Physics
  • Is Part Of: Journal of physics. Conference series, 2023-05, Vol.2504 (1), p.12016
  • Description: Abstract In this paper, we propose a simple and effective complementary label learning approach to address the label noise problem for deep learning model. Different surrogate losses have been proposed for complementary label learning, however, are often sophisticated designed, as the losses are required to satisfy the classifier consistency property. We propose an effective square loss for complementary label learning under unbiased and biased assumptions. We also show theoretically that our method assurances that the optimal classifier under complementary labels is also the optimal classifier under ordinary labels. Finally, we test our method on three different benchmark datasets with biased and unbiased assumptions to verify the effectiveness of our method.
  • Publisher: Bristol: IOP Publishing
  • Language: English
  • Identifier: ISSN: 1742-6588
    EISSN: 1742-6596
    DOI: 10.1088/1742-6596/2504/1/012016
  • Source: Open Access: IOP Publishing Free Content
    Geneva Foundation Free Medical Journals at publisher websites
    AUTh Library subscriptions: ProQuest Central
    IOPscience (Open Access)
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait