Knowledge Commons of Institute of Automation,CAS
Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking | |
Gao, Jin1![]() ![]() ![]() ![]() ![]() | |
发表期刊 | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
![]() |
ISSN | 0162-8828 |
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 |
DOI | 10.1109/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 | 否 |
引用统计 | |
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 |
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。
修改评论