Online Active Continual Learning for Robotic Lifelong Object Recognition

doi:10.1109/TNNLS.2023.3308900

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Online Active Continual Learning for Robotic Lifelong Object Recognition
	Nie, Xiangli 3,4; Deng, Zhiguang 2; He, Mingdong 2; Fan, Mingyu 5; Tang, Zheng 1
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2023-09-13
页码	15
关键词	Task analysis Robots Data models Object recognition Learning systems Training Heuristic algorithms Catastrophic forgetting lifelong object recognition online active learning (OAL) online continual learning (OCL)
ISSN号	2162-237X
DOI	10.1109/TNNLS.2023.3308900
通讯作者	Nie, Xiangli(xiangli.nie@ia.ac.cn) ; Tang, Zheng(adamtangzheng@163.com)
英文摘要	In real-world applications, robotic systems collect vast amounts of new data from ever-changing environments over time. They need to continually interact and learn new knowledge from the external world to adapt to the environment. Particularly, lifelong object recognition in an online and interactive manner is a crucial and fundamental capability for robotic systems. To meet this realistic demand, in this article, we propose an online active continual learning (OACL) framework for robotic lifelong object recognition, in the scenario of both classes and domains changing with dynamic environments. First, to reduce the labeling cost as much as possible while maximizing the performance, a new online active learning (OAL) strategy is designed by taking both the uncertainty and diversity of samples into account to protect the information volume and distribution of data. In addition, to prevent catastrophic forgetting and reduce memory costs, a novel online continual learning (OCL) algorithm is proposed based on the deep feature semantic augmentation and a new loss-based deep model and replay buffer update, which can mitigate the class imbalance between the old and new classes and alleviate confusion between two similar classes. Moreover, the mistake bound of the proposed method is analyzed in theory. OACL allows robots to select the most representative new samples to query labels and continually learn new objects and new variants of previously learned objects from a nonindependent and identically distributed (i.i.d.) data stream without catastrophic forgetting. Extensive experiments conducted on real lifelong robotic vision datasets demonstrate that our algorithm, even trained with fewer labeled samples and replay exemplars, can achieve state-of-the-art performance on OCL tasks.
资助项目	National Natural Science Foundation of China (NNSFC)[62076241] ; National Natural Science Foundation of China (NNSFC)[91948303] ; Beijing Nova Program[61933001] ; China Electronics Technology Group Corporation (CETC) Key Laboratory of DataLink Technology[20220484070] ; [CLDL-20202208_1]
WOS关键词	PERCEPTRON
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001068974800001
资助机构	National Natural Science Foundation of China (NNSFC) ; Beijing Nova Program ; China Electronics Technology Group Corporation (CETC) Key Laboratory of DataLink Technology
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53158]
专题	多模态人工智能系统全国重点实验室
通讯作者	Nie, Xiangli; Tang, Zheng
作者单位	1.China Elect Technol Grp Corp, Res Inst 20, Key Lab Data Link Technol, Xian 710068, Peoples R China 2.Beihang Univ, Sch Software, Beijing 100191, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 5.Donghua Univ, Inst Artificial Intelligence, Shanghai 200051, Peoples R China
推荐引用方式 GB/T 7714	Nie, Xiangli,Deng, Zhiguang,He, Mingdong,et al. Online Active Continual Learning for Robotic Lifelong Object Recognition[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2023:15.
APA	Nie, Xiangli,Deng, Zhiguang,He, Mingdong,Fan, Mingyu,&Tang, Zheng.(2023).Online Active Continual Learning for Robotic Lifelong Object Recognition.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,15.
MLA	Nie, Xiangli,et al."Online Active Continual Learning for Robotic Lifelong Object Recognition".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023):15.