Institute of Computing Technology, Chinese Academy IR
Transferring Boosted Detectors Towards Viewpoint and Scene Adaptiveness | |
Pang, Junbiao1,2; Huang, Qingming1,2; Yan, Shuicheng3; Jiang, Shuqiang2; Qin, Lei2 | |
2011-05-01 | |
发表期刊 | IEEE TRANSACTIONS ON IMAGE PROCESSING |
ISSN | 1057-7149 |
卷号 | 20期号:5页码:1388-1400 |
摘要 | In object detection, disparities in distributions between the training samples and the test ones are often inevitable, resulting in degraded performance for application scenarios. In this paper, we focus on the disparities caused by viewpoint and scene changes and propose an efficient solution to these particular cases by adapting generic detectors, assuming boosting style. A pretrained boosting-style detector encodes a priori knowledge in the form of selected features and weak classifier weighting. Towards adaptiveness, the selected features are shifted to the most discriminative locations and scales to compensate for the possible appearance variations. Moreover, the weighting coefficients are further adapted with covariate boost, which maximally utilizes the related training data to enrich the limited new examples. Extensive experiments validate the proposed adaptation mechanism towards viewpoint and scene adaptiveness and show encouraging improvement on detection accuracy over state-of-the-art methods. |
关键词 | Boosting covariate shift detector adaptiveness object detection transfer learning |
DOI | 10.1109/TIP.2010.2103951 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[61025011] ; National Natural Science Foundation of China[60833006] ; National Natural Science Foundation of China[61035001] ; National Basic Research Program of China (973 Program)[2009CB320906] ; Beijing Natural Science Foundation[4092042] ; NRF/IDM[NRF2008IDM-IDM004-029] |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000289844400017 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://119.78.100.204/handle/2XEOYT63/12733 |
专题 | 中国科学院计算技术研究所期刊论文_英文 |
通讯作者 | Pang, Junbiao |
作者单位 | 1.Chinese Acad Sci, Grad Univ, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Natl Univ Singapore, Dept Elect & Comp Engn, Singapore 11756, Singapore |
推荐引用方式 GB/T 7714 | Pang, Junbiao,Huang, Qingming,Yan, Shuicheng,et al. Transferring Boosted Detectors Towards Viewpoint and Scene Adaptiveness[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2011,20(5):1388-1400. |
APA | Pang, Junbiao,Huang, Qingming,Yan, Shuicheng,Jiang, Shuqiang,&Qin, Lei.(2011).Transferring Boosted Detectors Towards Viewpoint and Scene Adaptiveness.IEEE TRANSACTIONS ON IMAGE PROCESSING,20(5),1388-1400. |
MLA | Pang, Junbiao,et al."Transferring Boosted Detectors Towards Viewpoint and Scene Adaptiveness".IEEE TRANSACTIONS ON IMAGE PROCESSING 20.5(2011):1388-1400. |
条目包含的文件 | 条目无相关文件。 |
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