Learning Coexistence Discriminative Features for Multi-Class Object Detection

doi:10.1109/ACCESS.2018.2852728

	Learning Coexistence Discriminative Features for Multi-Class Object Detection
	Yao, Chao 1,2; Sun, Pengfei 1; Zhi, Ruicong 2; Shen, Yanfei 3,4
	2018
发表期刊	IEEE ACCESS
ISSN	2169-3536
卷号	6 页码:37676-37684
摘要	Existing methods on object detection have the ability to learn the discriminative features of local regions for object recognition; however, the coexistence relation between the multi-class objects could also benefit recognition. In this paper, we propose to learn the coexistence discriminative features for multi-class object detection. Given an image with multiple class objects, the strong supervision of the region-based annotations are first used as the image-level label to learn the independent discriminative features for each class. Then, the coexistence relation is fused as coexistence feature based on the attention mechanism. By combining the independent discriminative features and coexistence feature, the classification performance of multi-class object proposals can be consistently improved. Experimental results prove that the proposed end-to-end network outperforms the state-of-the-art object detection approaches, and the learned discriminative features can effectively capture the coexistence relations to improve classification performance of multi-class objects in the object detection task.
关键词	Object detection faster R-CNN coexistence relation multi-class objects class attention map
DOI	10.1109/ACCESS.2018.2852728
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61471343] ; National Natural Science Foundation of China[61701036] ; Fundamental Research Funds for the Central Universities[2017RC52]
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:000439698700097
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：16[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/4561
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhi, Ruicong; Shen, Yanfei
作者单位	1.Beijing Univ Posts & Telecommun, Inst Sensing Technol & Business, Beijing 100876, Peoples R China 2.Univ Sci & Technol Beijing, Sch Comp & Commun Engn, Beijing 10083, Peoples R China 3.Beijing Sport Univ, Sports & Engn Coll, Beijing 100084, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Yao, Chao,Sun, Pengfei,Zhi, Ruicong,et al. Learning Coexistence Discriminative Features for Multi-Class Object Detection[J]. IEEE ACCESS,2018,6:37676-37684.
APA	Yao, Chao,Sun, Pengfei,Zhi, Ruicong,&Shen, Yanfei.(2018).Learning Coexistence Discriminative Features for Multi-Class Object Detection.IEEE ACCESS,6,37676-37684.
MLA	Yao, Chao,et al."Learning Coexistence Discriminative Features for Multi-Class Object Detection".IEEE ACCESS 6(2018):37676-37684.