Enhancing Cross-View Object Classification by Feature-Based Transfer Learning
文献类型：会议论文
| 作者 | Yi Mo; Zhaoxiang Zhang ; Yunhong Wang
|
| 出版日期 | 2012-11-11 |
| 会议日期 | 11-15 November 2012 |
| 会议地点 | Tsukuba, Japan |
| 关键词 | Accuracy Vectors Training Surveillance Joints Manuals Pattern Recognition |
| 英文摘要 | Object classification is of vital importance to intelligent traffic surveillance. A big challenge is that shooting view changes in different scenes, which leads to sharp accuracy decrease since training and test samples do not follow the same distribution anymore. On the other hand, manual labeling training samples is time and labor consuming. We propose a feature-based transfer learning framework to gap the divergence of different domain distributions with scarce target view samples. Source view samples, following a different but relevant distribution, could be utilized to learn what a good classifier is like by structure learning. At the same time, small amount of target view samples could make a great contribution to reflect the target distribution. Experimental results indicate that our method outperforms traditional approaches when target samples are too scarce to build a strong classifier. |
| 会议录 | ICPR 2012
 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/13261]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Zhaoxiang Zhang |
| 推荐引用方式 GB/T 7714 | Yi Mo,Zhaoxiang Zhang,Yunhong Wang. Enhancing Cross-View Object Classification by Feature-Based Transfer Learning[C]. 见:. Tsukuba, Japan. 11-15 November 2012. |
入库方式： OAI收割
来源：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。