Self-Paced AutoEncoder

doi:10.1109/LSP.2018.2843295

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 先进时空数据分析与学习

	Self-Paced AutoEncoder
	Yu, Tingzhao1,2 ; Guo, Chaoxu1,2 ; Wang, Lingfeng1 ; Xiang, Shiming1 ; Pan, Chunhong1
发表期刊	IEEE SIGNAL PROCESSING LETTERS
ISSN	1070-9908
	2018-07-01
卷号	25 期号:7 页码:1054-1058
通讯作者	Yu, Tingzhao(tingzhao.yu@nlpr.ia.ac.cn)
摘要	Autoencoder, which learns latent representations of samples in an unsupervised manner, has great potential in computer vision and signal processing. However, the diversity of samples makes learning a component autoencoder remaining a challenging task. This letter proposes a novel Self-Paced AutoEncoder (SPAE) for unsupervised feature extraction. The motivation behind this letter is to take samples gradually from simple to complex into consideration during training, which is similar to the mechanism of knowledge acquisition for humans. Under the unsupervised learning framework constructed on the autoencoder infrastructure, our SPAE first learns a weak autoencoder via samples with small losses and, then, elevates itself to a relatively strong autoencoder through samples with large losses. Then, the SPAE is generalized to a temporal domain, resulting to temporal SPAE (TSPAE), where the temporal information is explored and exploited to improve the performance. Typically, a TSPAE is capable of compressing temporal sequences into temporal-independent data. Experiments on the image classification and action recognition demonstrate the effectiveness of SPAE and TSPAE.
关键词	Autoencoder (AE) self-paced learning (SPL) temporal encoding (TE) video analysis
DOI	10.1109/LSP.2018.2843295
关键词[WOS]	REPRESENTATION
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[61573352] ; National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[61573352] ; National Natural Science Foundation of China[61773377]
项目资助者	National Natural Science Foundation of China
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000435520200006
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：14[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/173211/23619
专题	多模态人工智能系统全国重点实验室_先进时空数据分析与学习
通讯作者	Yu, Tingzhao
作者单位	1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 101408, Peoples R China
第一作者单位	模式识别国家重点实验室
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	Yu, Tingzhao,Guo, Chaoxu,Wang, Lingfeng,et al. Self-Paced AutoEncoder[J]. IEEE SIGNAL PROCESSING LETTERS,2018,25(7):1054-1058.
APA	Yu, Tingzhao,Guo, Chaoxu,Wang, Lingfeng,Xiang, Shiming,&Pan, Chunhong.(2018).Self-Paced AutoEncoder.IEEE SIGNAL PROCESSING LETTERS,25(7),1054-1058.
MLA	Yu, Tingzhao,et al."Self-Paced AutoEncoder".IEEE SIGNAL PROCESSING LETTERS 25.7(2018):1054-1058.

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
[Tsingzao]Self-Paced（14078KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载