Deep unsupervised learning with consistent inference of latent representations
Chang, Jianlong1,2; Wang, Lingfeng1; Meng, Gaofeng1; Xiang, Shiming1,2; Pan, Chunhong1
发表期刊PATTERN RECOGNITION
2018-05-01
卷号77期号:5页码:438-453
文章类型Article
摘要Utilizing 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.
关键词Deep Unsupervised Learning Consistent Inference Of Latent Representations
WOS标题词Science & Technology ; Technology
DOI10.1016/j.patcog.2017.10.022
关键词[WOS]NEURAL-NETWORKS ; AUTO-ENCODERS ; RECOGNITION ; CLASSIFICATION ; ALGORITHM
收录类别SCI
语种英语
项目资助者National Natural Science Foundation of China (NSFC)(91646207 ; Beijing Nature Science Foundation(4162064) ; Youth Innovation Promotion Association CAS ; 61403376 ; 61370039 ; 91338202)
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000426222800033
引用统计
被引频次:12[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/173211/20364
专题模式识别国家重点实验室_先进时空数据分析与学习
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
第一作者单位模式识别国家重点实验室
推荐引用方式
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.
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
chang-pr-2018.pdf(2654KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Chang, Jianlong]的文章
[Wang, Lingfeng]的文章
[Meng, Gaofeng]的文章
百度学术
百度学术中相似的文章
[Chang, Jianlong]的文章
[Wang, Lingfeng]的文章
[Meng, Gaofeng]的文章
必应学术
必应学术中相似的文章
[Chang, Jianlong]的文章
[Wang, Lingfeng]的文章
[Meng, Gaofeng]的文章
相关权益政策
暂无数据
收藏/分享
文件名: chang-pr-2018.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。