A Hybrid Transfer Learning Mechanism for Object Classification across View
文献类型：会议论文
| 作者 | Yi Mo; Zhaoxiang Zhang ; Yunhong Wang
|
| 出版日期 | 2012-12-12 |
| 会议日期 | 12-15 December 2012 |
| 会议地点 | Boca Raton, Florida, USA |
| 关键词 | Transfer Learning Traffic Scene Surveillance Object Classification |
| 英文摘要 | Object classification in traffic scene is of vital importance to intelligent traffic surveillance. In real applications, the shooting view changes frequently in different scenes, which leads to sharp accuracy decrease since source and target domain samples do not follow the same distribution anymore. On the other hand, manual labeling training samples is time and labor consuming. Transfer learning approaches are to utilize the knowledge learnt from source view for target object classification. In this paper, we propose a hybrid transfer learning mechanism combining two single transfer approaches to gap the divergence of different domain distributions. An instance-based transfer approach is implemented to label target samples that represent target domain distribution best. And a feature-based transfer framework is to learn a strong classifier for target domain with both labeled source and target domain samples. Experimental results indicate that our approach outperforms traditional machine learning and single transfer learning methods. |
| 会议录 | ICMLA 2012
 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/13254]  |
| 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. A Hybrid Transfer Learning Mechanism for Object Classification across View[C]. 见:. Boca Raton, Florida, USA. 12-15 December 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。