Instance-level object retrieval via deep region CNN

doi:10.1007/s11042-018-6427-1

	Instance-level object retrieval via deep region CNN
	Mei, Shuhuan 1,2; Min, Weiqing 2; Duan, Hua 1; Jiang, Shuqiang 2,3
	2019-05-01
发表期刊	MULTIMEDIA TOOLS AND APPLICATIONS
ISSN	1380-7501
卷号	78 期号:10 页码:13247-13261
摘要	Instance retrieval is a fundamental problem in the multimedia field for its various applications. Since the relevancy is defined at the instance level, it is more challenging comparing to traditional image retrieval methods. Recent advances show that Convolutional Neural Networks (CNNs) offer an attractive method for image feature representations. However, the CNN method extracts features from the whole image, thus the extracted features contain a large amount of background noisy information, leading to poor retrieval performance. To solve the problem, this paper proposed a deep region CNN method with object detection for instance-level object retrieval, which has two phases, i.e., offline Faster R-CNN training and online instance retrieval. First, we train a Faster R-CNN model to better locate the region of the objects. Second, we extract the CNN features from the detected object image region and then retrieve relevant images based on the visual similarity of these features. Furthermore, we utilized three different strategies for feature fusing based on the detected object region candidates from Faster R-CNN. We conduct the experiment on a large dataset: INSTRE with 23,070 object images and additional one million distractor images. Qualitative and quantitative evaluation results have demonstrated the advantage of our proposed method. In addition, we conducted extensive experiments on the Oxford dataset and the experimental results further validated the effectiveness of our proposed method.
关键词	Faster R-CNN Deep learning Instance-level object retrieval Instre
DOI	10.1007/s11042-018-6427-1
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61532018] ; National Natural Science Foundation of China[61322212] ; National Natural Science Foundation of China[61602437] ; National Natural Science Foundation of China[61672497] ; National Natural Science Foundation of China[61472229] ; National Natural Science Foundation of China[61202152] ; Beijing Municipal Commission of Science and Technology[D161100001816001] ; Beijing Natural Science Foundation[4174106] ; Lenovo Outstanding Young Scientists Program ; National Program for Special Support of Eminent Professionals ; National Program for Support of Top-notch Young Professionals ; China Postdoctoral Science Foundation[2016M590135] ; China Postdoctoral Science Foundation[2017T100110] ; Science and Technology Development Fund of Shandong Province of China[2016ZDJS02A11] ; Science and Technology Development Fund of Shandong Province of China[ZR2017MF027] ; Taishan Scholar Climbing Program of Shandong Province ; SDUST Research Fund[2015TDJH102]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000471654900028
出版者	SPRINGER
引用统计	被引频次：4[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/2XEOYT63/4184
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Duan, Hua
作者单位	1.Shandong Univ Sci & Technol, Coll Math & Syst Sci, Qingdao 266590, Shandong, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Mei, Shuhuan,Min, Weiqing,Duan, Hua,et al. Instance-level object retrieval via deep region CNN[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2019,78(10):13247-13261.
APA	Mei, Shuhuan,Min, Weiqing,Duan, Hua,&Jiang, Shuqiang.(2019).Instance-level object retrieval via deep region CNN.MULTIMEDIA TOOLS AND APPLICATIONS,78(10),13247-13261.
MLA	Mei, Shuhuan,et al."Instance-level object retrieval via deep region CNN".MULTIMEDIA TOOLS AND APPLICATIONS 78.10(2019):13247-13261.