CASIA OpenIR  > 多模态人工智能系统全国重点实验室  > 视频内容安全
Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking
Gao, Jin1,2; Hu, Weiming1,2; Lu, Yan3
2020-06
Conference NameIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Conference Date2020-06-14至2020-06-19
Conference PlaceVirtual, United States
Abstract

Online learning is crucial to robust visual object track- ing as it can provide high discrimination power in the pres- ence of background distractors. However, there are two contradictory factors affecting its successful deployment on the real visual tracking platform: the discrimination issue due to the challenges in vanilla gradient descent, which does not guarantee good convergence; the robustness is- sue due to over-fitting resulting from excessive update with limited memory size (the oldest samples are discarded).

Despite many dedicated techniques proposed to some- how treat those issues, in this paper we take a new way to strike a compromise between them based on the recursive least-squares estimation (LSE) algorithm. After connect- ing each fully-connected layer with LSE separately via nor- mal equations, we further propose an improved mini-batch stochastic gradient descent algorithm for fully-connected network learning with memory retention in a recursive fash- ion. This characteristic can spontaneously reduce the risk of over-fitting resulting from catastrophic forgetting in ex- cessive online learning. Meanwhile, it can effectively im- prove convergence though the cost function is computed over all the training samples that the algorithm has ever seen. We realize this recursive LSE-aided online learning technique in the state-of-the-art RT-MDNet tracker, and the consistent improvements on four challenging benchmarks prove its efficiency without additional offline training and too much tedious work on parameter adjusting.

Indexed ByEI
Sub direction classification目标检测、跟踪与识别
planning direction of the national heavy laboratory实体人工智能系统感认知
Paper associated data
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/57513
Collection多模态人工智能系统全国重点实验室_视频内容安全
Corresponding AuthorGao, Jin
Affiliation1.NLPR, Institute of Automation, CAS
2.University of Chinese Academy of Sciences
3.Microsoft Research
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Gao, Jin,Hu, Weiming,Lu, Yan. Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking[C],2020.
Files in This Item: Download All
File Name/Size DocType Version Access License
Recursive_Least-Squa(468KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Gao, Jin]'s Articles
[Hu, Weiming]'s Articles
[Lu, Yan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Gao, Jin]'s Articles
[Hu, Weiming]'s Articles
[Lu, Yan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Gao, Jin]'s Articles
[Hu, Weiming]'s Articles
[Lu, Yan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Recursive_Least-Squares_Estimator-Aided_Online_Learning_for_Visual_Tracking.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.