CASIA OpenIR  > 模式识别国家重点实验室  > 先进数据分析与学习
Deep unsupervised learning with consistent inference of latent representations
Chang, Jianlong1,2; Wang, Lingfeng1; Meng, Gaofeng1; Xiang, Shiming1,2; Pan, Chunhong1
Source PublicationPATTERN RECOGNITION
2018-05-01
Volume77Issue:5Pages:438-453
SubtypeArticle
AbstractUtilizing unlabeled data to train deep neural networks (DNNs) is a crucial but challenging task. In this paper, we propose an end-to-end approach to tackle this problem with consistent inference of latent representations. Specifically, each unlabeled data point is considered as a seed to generate a set of latent labeled data points by adding various random disturbances or transformations. Under the expectation maximization framework, DNNs can be trained in an unsupervised way by minimizing the distances between the data points with the same latent representations. Furthermore, several variants of our approach can be derived by applying regularized and sparse constraints during optimization. Theoretically, the convergence of the proposed method and its variants are fully analyzed. Experimental results show that the proposed approach can significantly improve the performance on various tasks, including image classification and clustering. Such results also indicate that our method can guide DNNs to learn more invariant feature representations in comparison with traditional unsupervised methods. (C) 2017 Elsevier Ltd. All rights reserved.
KeywordDeep Unsupervised Learning Consistent Inference Of Latent Representations
WOS HeadingsScience & Technology ; Technology
DOI10.1016/j.patcog.2017.10.022
WOS KeywordNEURAL-NETWORKS ; AUTO-ENCODERS ; RECOGNITION ; CLASSIFICATION ; ALGORITHM
Indexed BySCI
Language英语
Funding OrganizationNational Natural Science Foundation of China (NSFC)(91646207 ; Beijing Nature Science Foundation(4162064) ; Youth Innovation Promotion Association CAS ; 61403376 ; 61370039 ; 91338202)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000426222800033
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/20364
Collection模式识别国家重点实验室_先进数据分析与学习
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
Recommended Citation
GB/T 7714
Chang, Jianlong,Wang, Lingfeng,Meng, Gaofeng,et al. Deep unsupervised learning with consistent inference of latent representations[J]. PATTERN RECOGNITION,2018,77(5):438-453.
APA Chang, Jianlong,Wang, Lingfeng,Meng, Gaofeng,Xiang, Shiming,&Pan, Chunhong.(2018).Deep unsupervised learning with consistent inference of latent representations.PATTERN RECOGNITION,77(5),438-453.
MLA Chang, Jianlong,et al."Deep unsupervised learning with consistent inference of latent representations".PATTERN RECOGNITION 77.5(2018):438-453.
Files in This Item: Download All
File Name/Size DocType Version Access License
chang-pr-2018.pdf(2654KB)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
[Chang, Jianlong]'s Articles
[Wang, Lingfeng]'s Articles
[Meng, Gaofeng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chang, Jianlong]'s Articles
[Wang, Lingfeng]'s Articles
[Meng, Gaofeng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chang, Jianlong]'s Articles
[Wang, Lingfeng]'s Articles
[Meng, Gaofeng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: chang-pr-2018.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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