Relative Forest for Visual Attribute Prediction

doi:10.1109/TIP.2016.2580939

	Relative Forest for Visual Attribute Prediction
	Li, Shaoxin 1; Shan, Shiguang 2; Yan, Shuicheng 3; Chen, Xilin 2
	2016-09-01
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	25 期号:9 页码:13
摘要	Accurate prediction of the visual attributes is significant in various recognition tasks. For many visual attributes, while it is very difficult to describe the exact degrees of their presences, by comparing the pairs of samples, the relative ordering of presences may be easily figured out. Based on this observation, instead of considering such attribute as binary attribute, the relative attribute method learns a ranking function for each attribute to provide more accurate and informative prediction results. In this paper, we also explore pairwise ranking for visual attribute prediction and propose to improve the relative attribute method in two aspects. First, we propose a relative tree method, which can achieve more accurate ranking in case of nonlinearly distributed visual data. Second, by resorting to randomization and ensemble learning, the relative tree method is extended to the relative forest method to further boost the accuracy and simultaneously reduce the computational cost. To validate the effectiveness of the proposed methods, we conduct extensive experiments on four databases: PubFig, OSR, FGNET, and WebFace. The results show that the proposed relative forest method not only outperforms the original relative attribute method, but also achieve the state-of-the-art accuracy for ordinal visual attribute prediction.
关键词	Visual attributes relative attributes random forest relative forest
DOI	10.1109/TIP.2016.2580939
收录类别	SCI
语种	英语
资助项目	973 Program[2015CB351802] ; Natural Science Foundation of China[61390511] ; Natural Science Foundation of China[61402443] ; Strategic Priority Research Program through the Chinese Academy of Sciences[XDB02070004]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000379900300003
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：3[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/2XEOYT63/8269
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Shan, Shiguang
作者单位	1.Tencent YouTu Lab, Tencent Shanghai 200233, Peoples R China 2.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 3.360 AI Inst, Beijing 100015, Peoples R China
推荐引用方式 GB/T 7714	Li, Shaoxin,Shan, Shiguang,Yan, Shuicheng,et al. Relative Forest for Visual Attribute Prediction[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2016,25(9):13.
APA	Li, Shaoxin,Shan, Shiguang,Yan, Shuicheng,&Chen, Xilin.(2016).Relative Forest for Visual Attribute Prediction.IEEE TRANSACTIONS ON IMAGE PROCESSING,25(9),13.
MLA	Li, Shaoxin,et al."Relative Forest for Visual Attribute Prediction".IEEE TRANSACTIONS ON IMAGE PROCESSING 25.9(2016):13.