Unsupervised Cross-View Semantic Transfer for Remote Sensing Image Classification

被引:60
作者
Sun, Hao [1 ]
Liu, Shuai [1 ]
Zhou, Shilin [1 ]
Zou, Huanxin [1 ]
机构
[1] Natl Univ Def Technol, Coll Elect Sci & Engn, Changsha 410072, Hunan, Peoples R China
基金
中国国家自然科学基金;
关键词
Cross-view subspace alignment (SA); remote sensing image classification; semantic knowledge transfer; unsupervised visual domain adaptation (DA); DOMAIN ADAPTATION; ALIGNMENT;
D O I
10.1109/LGRS.2015.2491605
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
We address the problem of unsupervised visual domain adaptation for transferring scene category models and scene attribute models from ground view images to overhead view very high-resolution (VHR) remote sensing images. We introduce a discriminative cross-view subspace alignment algorithm where each view is represented by a subspace spanned by eigenvectors. The source subspace is created using partial least squares correlation, whereas the target subspace is constructed by principal component analysis. Then, a mapping that aligns the source subspace and the target subspace is learned by minimizing a Bregman matrix divergence function. Finally, we project the labeled source data into the target aligned source subspace and the unlabeled target data into the target subspace and perform classification. Experimental results demonstrate that it is possible to use a scene category model or a scene attribute model learned on a set of ground view scenes for classification of VHR remote sensing images. Furthermore, the transferred visual attribute-based representations are human understandable and the classification results are better or comparable with state-of-the-art methods.
引用
收藏
页码:13 / 17
页数:5
相关论文
共 24 条
[1]  
[Anonymous], 2008, P ADV NEUR INF PROC
[2]   Pyramid of Spatial Relatons for Scene-Level Land Use Classification [J].
Chen, Shizhi ;
Tian, YingLi .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2015, 53 (04) :1947-1957
[3]   Unsupervised Feature Learning for Aerial Scene Classification [J].
Cheriyadat, Anil M. .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2014, 52 (01) :439-451
[4]   Satellite Image Classification via Two-Layer Sparse Coding With Biased Image Representation [J].
Dai, Dengxin ;
Yang, Wen .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2011, 8 (01) :173-176
[5]  
Farhadi A, 2009, PROC CVPR IEEE, P1778, DOI 10.1109/CVPRW.2009.5206772
[6]   Unsupervised Visual Domain Adaptation Using Subspace Alignment [J].
Fernando, Basura ;
Habrard, Amaury ;
Sebban, Marc ;
Tuytelaars, Tinne .
2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2013, :2960-2967
[7]   Learning Kernels for Unsupervised Domain Adaptation with Applications to Visual Object Recognition [J].
Gong, Boqing ;
Grauman, Kristen ;
Sha, Fei .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2014, 109 (1-2) :3-27
[8]  
Gopalan R, 2011, IEEE I CONF COMP VIS, P999, DOI 10.1109/ICCV.2011.6126344
[9]   Classifying Compound Structures in Satellite Images: A Compressed Representation for Fast Queries [J].
Gueguen, Lionel .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2015, 53 (04) :1803-1818
[10]  
Lampert CH, 2009, PROC CVPR IEEE, P951, DOI 10.1109/CVPRW.2009.5206594