Learning With Auxiliary Less-Noisy Labels

doi:10.1109/TNNLS.2016.2546956

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 视频内容安全

	Learning With Auxiliary Less-Noisy Labels
	Duan, Yunyan 1,2; Wu, Ou3
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2017-07-01
卷号	28 期号:7 页码:1716-1721
文章类型	Article
摘要	111111; 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.
关键词	Maximum Likelihood Approach Noisy Degrees Noisy Labels Soft Constraints
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TNNLS.2016.2546956
收录类别	SCI
语种	英语
项目资助者	NSFC(61379098)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000404048300020
引用统计	被引频次：16[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12022
专题	多模态人工智能系统全国重点实验室_视频内容安全
通讯作者	Wu, Ou
作者单位	1.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
通讯作者单位	模式识别国家重点实验室
推荐引用方式 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.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
yunyanduan.pdf（1315KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载