Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework

doi:10.1109/TPAMI.2018.2836461

	Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework
	Liang, Kongming 1,2; Chang, Hong 1,2; Ma, Bingpeng 1,2; Shan, Shiguang 1,2,3; Chen, Xilin 1,2
	2019-07-01
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
卷号	41 期号:7 页码:1747-1760
摘要	Attributes are mid-level semantic properties of objects. Recent research has shown that visual attributes can benefit many typical learning problems in computer vision community. However, attribute learning is still a challenging problem as the attributes may not always be predictable directly from input images and the variation of visual attributes is sometimes large across categories. In this paper, we propose a unified multiplicative framework for attribute learning, which tackles the key problems. Specifically, images and category information are jointly projected into a shared feature space, where the latent factors are disentangled and multiplied to fulfil attribute prediction. The resulting attribute classifier is category-specific instead of being shared by all categories. Moreover, our model can leverage auxiliary data to enhance the predictive ability of attribute classifiers, which can reduce the effort of instance-level attribute annotation to some extent. By integrated into an existing deep learning framework, our model can both accurately predict attributes and learn efficient image representations. Experimental results show that our method achieves superior performance on both instance-level and category-level attribute prediction. For zero-shot learning based on visual attributes and human-object interaction recognition, our method can improve the state-of-the-art performance on several widely used datasets.
关键词	Attribute learning zero-shot learning image understanding
DOI	10.1109/TPAMI.2018.2836461
收录类别	SCI
语种	英语
资助项目	973 Program[2015CB351802] ; Natural Science Foundation of China (NSFC)[61390515] ; Natural Science Foundation of China (NSFC)[61390511] ; Natural Science Foundation of China (NSFC)[61572465] ; Natural Science Foundation of China (NSFC)[61650202]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000470972300017
出版者	IEEE COMPUTER SOC
引用统计	被引频次：11[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/2XEOYT63/4166
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Chang, Hong
作者单位	1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Liang, Kongming,Chang, Hong,Ma, Bingpeng,et al. Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2019,41(7):1747-1760.
APA	Liang, Kongming,Chang, Hong,Ma, Bingpeng,Shan, Shiguang,&Chen, Xilin.(2019).Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,41(7),1747-1760.
MLA	Liang, Kongming,et al."Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 41.7(2019):1747-1760.