CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Learning With Auxiliary Less-Noisy Labels
Duan, Yunyan1,2; Wu, Ou3
Source PublicationIEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
2017-07-01
Volume28Issue:7Pages:1716-1721
SubtypeArticle
Abstract111111; Obtaining a sufficient number of accurate labels to form a training set for learning a classifier can be difficult due to the limited access to reliable label resources. Instead, in real-world applications, less-accurate labels, such as labels from nonexpert labelers, are often used. However, learning with less-accurate labels can lead to serious performance deterioration because of the high noise rate. Although several learning methods (e.g., noise-tolerant classifiers) have been advanced to increase classification performance in the presence of label noise, only a few of them take the noise rate into account and utilize both noisy but easily accessible labels and less-noisy labels, a small amount of which can be obtained with an acceptable added time cost and expense. In this brief, we propose a learning method, in which not only noisy labels but also auxiliary less-noisy labels, which are available in a small portion of the training data, are taken into account. Based on a flipping probability noise model and a logistic regression classifier, this method estimates the noise rate parameters, infers ground-truth labels, and learns the classifier simultaneously in a maximum likelihood manner. The proposed method yields three learning algorithms, which correspond to three prior knowledge states regarding the less-noisy labels. The experiments show that the proposed method is tolerant to label noise, and outperforms classifiers that do not explicitly consider the auxiliary less-noisy labels.
KeywordMaximum Likelihood Approach Noisy Degrees Noisy Labels Soft Constraints
WOS HeadingsScience & Technology ; Technology
DOI10.1109/TNNLS.2016.2546956
Indexed BySCI
Language英语
Funding OrganizationNSFC(61379098)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS IDWOS:000404048300020
Citation statistics
Cited Times:4[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12022
Collection模式识别国家重点实验室_视频内容安全
Corresponding AuthorWu, Ou
Affiliation1.Peking Univ, Sch Math Sci, Beijing 100871, Peoples R China
2.Northwestern Univ, Dept Linguist, Evanston, IL 60201 USA
3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Duan, Yunyan,Wu, Ou. Learning With Auxiliary Less-Noisy Labels[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2017,28(7):1716-1721.
APA Duan, Yunyan,&Wu, Ou.(2017).Learning With Auxiliary Less-Noisy Labels.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,28(7),1716-1721.
MLA Duan, Yunyan,et al."Learning With Auxiliary Less-Noisy Labels".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 28.7(2017):1716-1721.
Files in This Item: Download All
File Name/Size DocType Version Access License
yunyanduan.pdf(1315KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Duan, Yunyan]'s Articles
[Wu, Ou]'s Articles
Baidu academic
Similar articles in Baidu academic
[Duan, Yunyan]'s Articles
[Wu, Ou]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Duan, Yunyan]'s Articles
[Wu, Ou]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: yunyanduan.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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