DFLLR: Deep Feature Learning With Latent Relationship Embedding for Remote Sensing Image Retrieval

被引:6
作者
Liu, Li [1 ,2 ]
Wang, Yuebin [1 ,2 ]
Peng, Junhuan [1 ,2 ]
Plaza, Antonio [3 ]
机构
[1] China Univ Geosci Beijing, Sch Land Sci & Technol, Beijing 100083, Peoples R China
[2] Shanxi Prov Key Lab Resources Environm & Disaster, Jinzhong 030600, Peoples R China
[3] Univ Extremadura, Dept Technol Comp & Commun, Hyperspectral Comp Lab, Escuela Politecn, Caceres 10003, Spain
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2022年 / 60卷
基金
中国国家自然科学基金;
关键词
Feature extraction; Image retrieval; Remote sensing; Visualization; Task analysis; Semantics; Manifolds; Central constraint; deep networks; latent relationships; margin constraint; remote sensing image retrieval (RSIR);
D O I
10.1109/TGRS.2021.3097361
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
For deep networks, accurate image similarities cannot be well characterized with limited iterations, so the latent relationships between images can be embedded to enhance image retrieval performance. In this article, we propose a method named DFLLR to learn deep image features and accurate image similarities for remote sensing image retrieval (RSIR) simultaneously. First, the AlexNet is employed to extract high-level semantic features. Second, to obtain accurate image similarities, latent relationships between images are constructed with manifold learning and embedded in the AlexNet model with fully connected layers; in this way, the latent relationships and image features can be jointly learned. Third, to boost the RSIR performance further, the constraints of central and margin for jointly learning latent relationships and image features are integrated into our DFLLR. The central constraint is used to reduce the discrepancy of the latent relationships at the intraclass level and enhance the accuracies of image features. Moreover, the margin constraint is designed to enhance the accuracies of the latent relationships by maximizing the manifold margin between the latent relationships at the intraclass and interclass levels. To validate our method, we perform comprehensive experiments on three publicly available remote sensing image datasets, and the results demonstrate that it significantly outperforms other state-of-the-art methods.
引用
收藏
页数:14
相关论文
共 42 条
[1]   Remote Sensing Image Retrieval With Global Morphological Texture Descriptors [J].
Aptoula, Erchan .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2014, 52 (05) :3023-3034
[2]   Speeded-Up Robust Features (SURF) [J].
Bay, Herbert ;
Ess, Andreas ;
Tuytelaars, Tinne ;
Van Gool, Luc .
COMPUTER VISION AND IMAGE UNDERSTANDING, 2008, 110 (03) :346-359
[3]   Enhancing remote sensing image retrieval using a triplet deep metric learning network [J].
Cao, Rui ;
Zhang, Qian ;
Zhu, Jiasong ;
Li, Qing ;
Li, Qingquan ;
Liu, Bozhi ;
Qiu, Guoping .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2020, 41 (02) :740-751
[4]   The devil is in the details: an evaluation of recent feature encoding methods [J].
Chatfield, Ken ;
Lempitsky, Victor ;
Vedaldi, Andrea ;
Zisserman, Andrew .
PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2011, 2011,
[5]  
Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
[6]   Distribution Consistency Loss for Large-Scale Remote Sensing Image Retrieval [J].
Fan, Lili ;
Zhao, Hongwei ;
Zhao, Haoyu .
REMOTE SENSING, 2020, 12 (01)
[7]   An endmember-based distance for content based hyperspectral image retrieval [J].
Grana, Manuel ;
Veganzones, Miguel A. .
PATTERN RECOGNITION, 2012, 45 (09) :3472-3489
[8]   Aggregated Deep Local Features for Remote Sensing Image Retrieval [J].
Imbriaco, Raffaele ;
Sebastian, Clint ;
Bondarev, Egor ;
de With, Peter H. N. .
REMOTE SENSING, 2019, 11 (05)
[9]  
Jégou H, 2010, PROC CVPR IEEE, P3304, DOI 10.1109/CVPR.2010.5540039
[10]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90