Hybrid incremental learning of new data and new classes for hand-held object recognition

doi:10.1016/j.jvcir.2018.11.009

	Hybrid incremental learning of new data and new classes for hand-held object recognition
	Chen, Chengpeng 1,4; Min, Weiqing 2,3; Li, Xue 2; Jiang, Shuqiang 2,4
	2019
发表期刊	JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
ISSN	1047-3203
卷号	58 页码:138-148
摘要	Intelligence 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. (C) 2018 Elsevier Inc. All rights reserved.
关键词	Incremental learning Object recognition SVM Human-machine interaction
DOI	10.1016/j.jvcir.2018.11.009
收录类别	SCI
语种	英语
资助项目	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
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering
WOS记录号	WOS:000457668100015
出版者	ACADEMIC PRESS INC ELSEVIER SCIENCE
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/3447
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Jiang, Shuqiang
作者单位	1.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing, Peoples R China 3.Chinese Acad Sci, Shenyang Inst Automat, State Key Lab Robot, Shenyang, Liaoning, Peoples R China 4.Univ Chinese Acad Sci, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Chen, Chengpeng,Min, Weiqing,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, Weiqing,Li, Xue,&Jiang, Shuqiang.(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.