SIA OpenIR  > 机器人学研究室
Hybrid incremental learning of new data and new classes for hand-held object recognition
Chen, Chengpeng1,4; Min WQ(闵巍庆)2,3; Li, Xue2; Jiang SQ(蒋树强)2,4
Department机器人学研究室
Source PublicationJournal of Visual Communication and Image Representation
ISSN1047-3203
2019
Volume58Pages:138-148
Indexed BySCI ; EI
EI Accession number20184806160735
WOS IDWOS:000457668100015
Contribution Rank2
Funding OrganizationBeijing Natural Science Foundation ; National Natural Science Foundation of China ; Lenovo Outstanding Young Scientists Program ; National Program for Special Support of Eminent Professionals ; National Program for Support of Top-notch Young Professionals ; China Postdoctoral Science Foundation ; State Key Laboratory of Robotics
KeywordIncremental learning Object recognition SVM Human-machine interaction
AbstractIntelligence technology is an important research area. As a very special yet important case of object recognition, hand-held object recognition plays an important role in intelligence technology for its many applications such as visual question-answering and reasoning. In real-world scenarios, the datasets are open-ended and dynamic: new object samples and new object classes increase continuously. This requires the intelligence technology to enable hybrid incremental learning, which supports both data-incremental and class-incremental learning to efficiently learn the new information. However, existing work mainly focuses on one side of incremental learning, either data-incremental or class-incremental learning while do not handle two sides of incremental learning in a unified framework. To solve the problem, we present a Hybrid Incremental Learning (HIL) method based on Support Vector Machine (SVM), which can incrementally improve its recognition ability by learning new object samples and new object concepts during the interaction with humans. In order to integrate data-incremental and class-incremental learning into one unified framework, HIL adds the new classification-planes and adjusts existing classification-planes under the setting of SVM. As a result, our system can simultaneously improve the recognition quality of known concepts by minimizing the prediction error and transfer the previous model to recognize unknown objects. We apply the proposed method into hand-held object recognition and the experimental results demonstrated its advantage of HIL. In addition, we conducted extensive experiments on the subset of ImageNet and the experimental results further validated the effectiveness of the proposed method.
Language英语
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering
WOS KeywordCLASSIFICATION ; MECHANISMS ; FEATURES ; ONLINE
WOS Research AreaComputer Science
Funding ProjectBeijing Natural Science Foundation[4174106] ; National Natural Science Foundation of China[61532018] ; National Natural Science Foundation of China[61602437] ; Lenovo Outstanding Young Scientists Program ; National Program for Special Support of Eminent Professionals ; National Program for Support of Top-notch Young Professionals ; China Postdoctoral Science Foundation[2017T100110] ; State Key Laboratory of Robotics ; Beijing Natural Science Foundation[4174106] ; National Natural Science Foundation of China[61532018] ; National Natural Science Foundation of China[61602437] ; Lenovo Outstanding Young Scientists Program ; National Program for Special Support of Eminent Professionals ; National Program for Support of Top-notch Young Professionals ; China Postdoctoral Science Foundation[2017T100110] ; State Key Laboratory of Robotics
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/23670
Collection机器人学研究室
Corresponding AuthorJiang SQ(蒋树强)
Affiliation1.State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
2.Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
3.State key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
4.University of Chinese Academy of Sciences, Beijing, China
Recommended Citation
GB/T 7714
Chen, Chengpeng,Min WQ,Li, Xue,et al. Hybrid incremental learning of new data and new classes for hand-held object recognition[J]. Journal of Visual Communication and Image Representation,2019,58:138-148.
APA Chen, Chengpeng,Min WQ,Li, Xue,&Jiang SQ.(2019).Hybrid incremental learning of new data and new classes for hand-held object recognition.Journal of Visual Communication and Image Representation,58,138-148.
MLA Chen, Chengpeng,et al."Hybrid incremental learning of new data and new classes for hand-held object recognition".Journal of Visual Communication and Image Representation 58(2019):138-148.
Files in This Item: Download All
File Name/Size DocType Version Access License
Hybrid incremental l(2703KB)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
[Chen, Chengpeng]'s Articles
[Min WQ(闵巍庆)]'s Articles
[Li, Xue]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chen, Chengpeng]'s Articles
[Min WQ(闵巍庆)]'s Articles
[Li, Xue]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chen, Chengpeng]'s Articles
[Min WQ(闵巍庆)]'s Articles
[Li, Xue]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Hybrid incremental learning of new data and new classes for hand-held object recognition.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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