Lifelong Metric Learning
文献类型：期刊论文
| 作者 | Cong Y(丛杨)1; Liu LQ(刘连庆)1; Xu XW(徐晓伟)4; Liu J(刘霁)3; Yu HB(于海斌)1; Sun G(孙干)1; Liu JG(刘金国) ; Sun Q(孙强); Wang TJ(王铁军); Xiao L(肖磊)
|
| 刊名 | IEEE Transactions on Cybernetics
 |
| 出版日期 | 2018 |
| 页码 | 1-10 |
| 关键词 | Lifelong Learning Metric Learning Multi-task Learning Low-rank Subspace |
| ISSN号 | 2168-2267 |
| 产权排序 | 1 |
| 通讯作者 | Sun G(孙干) |
| 中文摘要 | The state-of-the-art online learning approaches are only capable of learning the metric for predefined tasks. In this paper, we consider a lifelong learning problem to mimic ``human learning,'' i.e., endowing a new capability to the learned metric for a new task from new online samples and incorporating the previous experiences. Therefore, we propose a new metric learning framework: lifelong metric learning (LML), which only utilizes the data of the new task to train the metric model while preserving the original capabilities. More specifically, the proposed LML maintains a common subspace for all learned metrics, named lifelong dictionary, transfers knowledge from the common subspace to learn each new metric learning task with task-specific idiosyncrasy, and redefines the common subspace over time to maximize performance across all metric tasks. For model optimization, we apply online passive aggressive optimization algorithm to achieve lifelong metric task learning, where the lifelong dictionary and task-specific partition are optimized alternatively and consecutively. Finally, we evaluate our approach by analyzing several multitask metric learning datasets. Extensive experimental results demonstrate effectiveness and efficiency of the proposed framework. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.sia.cn/handle/173321/22198]  |
| 专题 | 沈阳自动化研究所_空间自动化技术研究室 |
| 作者单位 | 1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 2.University of Chinese Academy of Sciences 3.Department of Computer Science, University of Rochester, Rochester, NY 14627 USA 4.Department of Information Science, University of Arkansas at Little Rock, Little Rock, AR 72204 USA |
| 推荐引用方式 GB/T 7714 | Cong Y,Liu LQ,Xu XW,et al. Lifelong Metric Learning[J]. IEEE Transactions on Cybernetics,2018:1-10. |
| APA | Cong Y.,Liu LQ.,Xu XW.,Liu J.,Yu HB.,...&陈科利.(2018).Lifelong Metric Learning.IEEE Transactions on Cybernetics,1-10. |
| MLA | Cong Y,et al."Lifelong Metric Learning".IEEE Transactions on Cybernetics (2018):1-10. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
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。