Enhancing Cross-View Object Classification by Feature-Based Transfer Learning

CASIA OpenIR > 智能感知与计算研究中心

	Enhancing Cross-View Object Classification by Feature-Based Transfer Learning
	Yi Mo; Zhaoxiang Zhang; Yunhong Wang
	2012-11-11
会议名称	International Conference on Pattern Recognition
会议录名称	ICPR 2012
会议日期	11-15 November 2012
会议地点	Tsukuba, Japan
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.
关键词	Accuracy Vectors Training Surveillance Joints Manuals Pattern Recognition
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/13261
专题	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],2012.