Knowledge Commons of Institute of Automation,CAS
Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking | |
Gao, Jin1,2![]() ![]() | |
2020-06 | |
会议名称 | IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
会议日期 | 2020-06-14至2020-06-19 |
会议地点 | Virtual, United States |
摘要 | 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. |
收录类别 | EI |
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 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57513 |
专题 | 多模态人工智能系统全国重点实验室_视频内容安全 |
通讯作者 | Gao, Jin |
作者单位 | 1.NLPR, Institute of Automation, CAS 2.University of Chinese Academy of Sciences 3.Microsoft Research |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Gao, Jin,Hu, Weiming,Lu, Yan. Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking[C],2020. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Recursive_Least-Squa(468KB) | 会议论文 | 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