Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking
Gao, Jin1; Lu, Yan2; Qi, Xiaojuan3; Kou, Yutong1; Li, Bing1; Li, Liang4; Yu, Shan1; Hu, Weiming1
发表期刊IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN0162-8828
2024
卷号46期号:3页码:1881-1897
通讯作者Hu, Weiming(wmhu@nlpr.ia.ac.cn)
摘要

Tracking visual objects from a single initial exemplar in the testing phase has been broadly cast as a one-/few-shot problem, i.e., one-shot learning for initial adaptation and few-shot learning for online adaptation. The recent few-shot online adaptation methods incorporate the prior knowledge from large amounts of annotated training data via complex meta-learning optimization in the offline phase. This helps the online deep trackers to achieve fast adaptation and reduce overfitting risk in tracking. In this paper, we propose a simple yet effective recursive least-squares estimator-aided online learning approach for few-shot onlineadaptation without requiring offline training. It allows an in-built memory retention mechanism for the model to remember the knowledge about the object seen before, and thus the seen data can be safely removed from training. This also bears certain similarities to the emerging continual learning field in preventing catastrophic forgetting. This mechanism enables us to unveil the power of modern online deep trackers without incurring too much extra computational cost. We evaluate our approach based on two networks in the online learning families for tracking, i.e., multi-layer perceptrons in RT-MDNet and convolutional neural networks in DiMP. The consistent improvements on several challenging tracking benchmarks demonstrate its effectiveness and efficiency.

关键词Visualization Training Adaptation models Data models Optimization Task analysis Robustness Online learning few-shot online adaptation visual tracking continual learning recursive least-squares estimation
DOI10.1109/TPAMI.2022.3156977
关键词[WOS]OBJECT TRACKING ; ROBUST
收录类别SCI
语种英语
资助项目National Key R#x0026;D Program of China
项目资助者National Key R#x0026;D Program of China
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:001174191100027
出版者IEEE COMPUTER SOC
七大方向——子方向分类目标检测、跟踪与识别
国重实验室规划方向分类实体人工智能系统感认知
是否有论文关联数据集需要存交
引用统计
被引频次:1[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/57500
专题多模态人工智能系统全国重点实验室_视频内容安全
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Microsoft Res Asia, Beijing 100080, Peoples R China
3.Univ Hong Kong, Dept Elect & Elect Engn, Hong Kong, Peoples R China
4.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
第一作者单位模式识别国家重点实验室
推荐引用方式
GB/T 7714
Gao, Jin,Lu, Yan,Qi, Xiaojuan,et al. Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2024,46(3):1881-1897.
APA Gao, Jin.,Lu, Yan.,Qi, Xiaojuan.,Kou, Yutong.,Li, Bing.,...&Hu, Weiming.(2024).Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,46(3),1881-1897.
MLA Gao, Jin,et al."Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 46.3(2024):1881-1897.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
TPAMI2024.pdf(915KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Gao, Jin]的文章
[Lu, Yan]的文章
[Qi, Xiaojuan]的文章
百度学术
百度学术中相似的文章
[Gao, Jin]的文章
[Lu, Yan]的文章
[Qi, Xiaojuan]的文章
必应学术
必应学术中相似的文章
[Gao, Jin]的文章
[Lu, Yan]的文章
[Qi, Xiaojuan]的文章
相关权益政策
暂无数据
收藏/分享
文件名: TPAMI2024.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。