BundleNet Learning with Noisy Label via Sample Correlations

doi:10.1109/ACCESS.2017.2782844

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 图像与视频分析团队

	BundleNet Learning with Noisy Label via Sample Correlations
	Li, Chenghua1,4 ; Zhang, Chunjie2,5 ; Ding, Kun2,4 ; Li, Gang1,4 ; Cheng, Jian1,4,6 ; Lu, Hanqing3,4 ; Jian Cheng
刊名	IEEE ACCESS
	2018
卷号	6 期号:1 页码:2367-2377
关键词	Bundlenet Sequential Data Classification Noisy Label Regularization
DOI	10.1109/ACCESS.2017.2782844
文献子类	Article
英文摘要	Sequential patterns are important, because they can be exploited to improve the prediction accuracy of our classifiers. Sequential data, such as time series/video frames, and event data are becoming more and more ubiquitous in a wide spectrum of application scenarios especially in the background of large data and deep learning. However, large data sets used in training modern machine-learning models, such as deep neural networks, are often affected by label noise. Existing noisy learning approaches mainly focus on building an additional network to clean the noise or find a robust loss function. Few works tackle this problem by exploiting sample correlations. In this paper, we propose BundleNet, a framework of sequential structure (named bundle-module, see Fig. 1) for deep neural networks to handle the label noise. The bundle module naturally takes into account sample correlations by constructing bundles of samples class-by-class, and treats them as independent inputs. Moreover, we prove that the bundle-module performs a form of regularization, which is similar to dropout as regularization during training. The regularization effect endows the BundleNet with strong robustness to the label noise. Extensive experiments on public data sets prove that the proposed approach is effective and promising.
WOS关键词	IMAGE CLASSIFICATION ; REPRESENTATION
WOS研究方向	Computer Science ; Engineering ; Telecommunications
语种	英语
WOS记录号	WOS:000426275700001
资助机构	National Natural Science Foundation of China(61332016) ; Jiangsu Key Laboratory of Big Data Analysis Technology ; 863 Program(2014AA015105)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/20899]
专题	自动化研究所_模式识别国家重点实验室_图像与视频分析团队
通讯作者	Jian Cheng
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Automat, Pattern Recognit & Intelligent Syst, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 5.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China 6.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Li, Chenghua,Zhang, Chunjie,Ding, Kun,et al. BundleNet Learning with Noisy Label via Sample Correlations[J]. IEEE ACCESS,2018,6(1):2367-2377.
APA	Li, Chenghua.,Zhang, Chunjie.,Ding, Kun.,Li, Gang.,Cheng, Jian.,...&Jian Cheng.(2018).BundleNet Learning with Noisy Label via Sample Correlations.IEEE ACCESS,6(1),2367-2377.
MLA	Li, Chenghua,et al."BundleNet Learning with Noisy Label via Sample Correlations".IEEE ACCESS 6.1(2018):2367-2377.