CASIA OpenIR
Un-supervised and semi-supervised hand segmentation in egocentric images with noisy label learning
Li, Yinlin1,2; Jia, Lihao3,4; Wang, Zidong5; Qian, Yang3,6; Qiao, Hong1,6,7,8
Source PublicationNEUROCOMPUTING
ISSN0925-2312
2019-03-21
Volume334Issue:2019Pages:11-24
Abstract

With the rapid development of wearable devices and technologies, hand segmentation remains a less explored direction in egocentric vision, which is very important for activity recognition, rehabilitation, robot self-learning, etc. To overcome the high cost of auxiliary equipment and pixel-level annotations, we present an un-supervised hand segmentation method for egocentric images. Firstly, a fully convolutional neural network (FCN) is pre-trained in source dataset containing pixel-level annotations. Then, in target dataset without labels, the network is re-trained with optimized masks, which are produced by modified local and global consistency learning (LLGC) based on pre-segmentation and superpixel features. Finally, hand segmentation is realized in an alternative way. Furthermore, to balance segmentation accuracy and the cost on labeling, we propose a new semi-supervised image segmentation framework with three subnets based on the optimized noisy masks and a small number of clean labeled data. Experimental results in two target datasets indicate that the proposed methods could achieve better performance than other methods. (C) 2019 Elsevier B.V. All rights reserved.

KeywordHand segmentation Un-supervised Semi-supervised Deep convolutional neural network Noisy label
DOI10.1016/j.neucom.2018.12.010
WOS KeywordRECOGNITION ; ALGORITHM ; GESTURE
Indexed BySCI
Language英语
Funding ProjectStrategic Priority Research Program of Chinese Academy of Science[XDB32000000] ; National Natural Science Foundation of China[61702323] ; National Natural Science Foundation of China[61502494] ; National Natural Science Foundation of China[51705515] ; National Natural Science Foundation of China (NSFC)[U1613213] ; National Natural Science Foundation of China (NSFC)[U1713201] ; National Key Research and Development Program of China[2017YFB1300203] ; National Key Research and Development Program of China[2017YFB1300200] ; National Natural Science Foundation of China[61702516] ; Development of Science and Technology of Guangdong Province Special Fund Project[2016B090910001] ; National Natural Science Foundation of China[91648205] ; National Natural Science Foundation of China[61627808] ; National Natural Science Foundation of China[61627808] ; National Natural Science Foundation of China[91648205] ; Development of Science and Technology of Guangdong Province Special Fund Project[2016B090910001] ; National Natural Science Foundation of China[61702516] ; National Key Research and Development Program of China[2017YFB1300200] ; National Key Research and Development Program of China[2017YFB1300203] ; National Natural Science Foundation of China (NSFC)[U1713201] ; National Natural Science Foundation of China (NSFC)[U1613213] ; National Natural Science Foundation of China[51705515] ; National Natural Science Foundation of China[61502494] ; National Natural Science Foundation of China[61702323] ; Strategic Priority Research Program of Chinese Academy of Science[XDB32000000]
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000458626300002
PublisherELSEVIER SCIENCE BV
Citation statistics
Cited Times:5[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/25041
Collection中国科学院自动化研究所
Corresponding AuthorQiao, Hong
Affiliation1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
2.Beijing Key Lab Res & Applicat Robot Intelligence, Beijing 100190, Peoples R China
3.Chinese Acad Sci, Res Ctr Brain Inspired Intelligence, Inst Automat, Beijing 100190, Peoples R China
4.Chinese Acad Sci, Cloud Comp Ctr, Dongguan 523808, Peoples R China
5.Brunel Univ, Dept Informat Syst & Comp, Uxbridge UB8 3PH, Middx, England
6.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
7.Univ Sci & Technol Beijing, Sch Mech Engn, Beijing 100083, Peoples R China
8.CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 200031, Peoples R China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Li, Yinlin,Jia, Lihao,Wang, Zidong,et al. Un-supervised and semi-supervised hand segmentation in egocentric images with noisy label learning[J]. NEUROCOMPUTING,2019,334(2019):11-24.
APA Li, Yinlin,Jia, Lihao,Wang, Zidong,Qian, Yang,&Qiao, Hong.(2019).Un-supervised and semi-supervised hand segmentation in egocentric images with noisy label learning.NEUROCOMPUTING,334(2019),11-24.
MLA Li, Yinlin,et al."Un-supervised and semi-supervised hand segmentation in egocentric images with noisy label learning".NEUROCOMPUTING 334.2019(2019):11-24.
Files in This Item: Download All
File Name/Size DocType Version Access License
NeuroComputing2018.p(4423KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li, Yinlin]'s Articles
[Jia, Lihao]'s Articles
[Wang, Zidong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li, Yinlin]'s Articles
[Jia, Lihao]'s Articles
[Wang, Zidong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li, Yinlin]'s Articles
[Jia, Lihao]'s Articles
[Wang, Zidong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: NeuroComputing2018.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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