General Incremental Learning with Domain-aware Categorical Representations

doi:10.1109/CVPR52688.2022.01395

	General Incremental Learning with Domain-aware Categorical Representations
	Xie, Jiangwei1 ; Yan, Shipeng1,3,4 ; He, Xuming1,2
	2022
会议录名称	PROCEEDINGS OF THE IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION
ISSN	1063-6919
卷号	2022-June
页码	14331-14340
发表状态	已发表
DOI	10.1109/CVPR52688.2022.01395
摘要	Continual learning is an important problem for achieving human-level intelligence in real-world applications as an agent must continuously accumulate knowledge in response to streaming data/tasks. In this work, we consider a general and yet under-explored incremental learning problem in which both the class distribution and class-specific domain distribution change over time. In addition to the typical challenges in class incremental learning, this setting also faces the intra-class stability-plasticity dilemma and intra-class domain imbalance problems. To address above issues, we develop a novel domain-aware continual learning method based on the EM framework. Specifically, we introduce a flexible class representation based on the von Mises-Fisher mixture model to capture the intra-class structure, using an expansion-and- reduction strategy to dynamically increase the number of components according to the class complexity. Moreover, we design a bi-level balanced memory to cope with data imbalances within and across classes, which combines with a distillation loss to achieve better inter- and intra-class stability-plasticity trade-off. We conduct exhaustive experiments on three benchmarks: iDigits, iDomainNet and iCIFAR-20. The results show that our approach consistently outperforms previous methods by a significant margin, demonstrating its superiority. © 2022 IEEE.
会议名称	2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
出版地	10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA
会议地点	New Orleans, LA, United states
会议日期	June 19, 2022 - June 24, 2022
URL	查看原文
收录类别	EI ; CPCI-S
语种	英语
资助项目	Shanghai Science and Technology Program[21010502700]
WOS研究方向	Computer Science ; Imaging Science & Photographic Technology
WOS类目	Computer Science, Artificial Intelligence ; Imaging Science & Photographic Technology
WOS记录号	WOS:000870759107042
出版者	IEEE Computer Society
EI入藏号	20224613119445
原始文献类型	Conference article (CA)
来源库	IEEE
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/248932
专题	信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_何旭明组信息科学与技术学院_博士生
通讯作者	Xie, Jiangwei
作者单位	1.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China 2.Shanghai Engn Res Ctr Intelligent Vis & Imaging, Shanghai, Peoples R China 3.Chinese Acad Sci, Shanghai Inst Microsyst & Informat Technol, Beijing, Peoples R China 4.Univ Chinese Acad Sci, Beijing, Peoples R China
第一作者单位	信息科学与技术学院
通讯作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Xie, Jiangwei,Yan, Shipeng,He, Xuming. General Incremental Learning with Domain-aware Categorical Representations[C]. 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA:IEEE Computer Society,2022:14331-14340.