中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 遥感图像处理团队
Triplet Adversarial Domain Adaptation for Pixel-Level Classification of VHR Remote Sensing Images

文献类型：期刊论文

作者Yan, Liang3,4; Fan, Bin3,4; Liu, Hongmin1,2; Huo, Chunlei4; Xiang, Shiming3,4; Pan, Chunhong4
刊名IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
出版日期2020-05-01
卷号58期号:5页码:3558-3573
关键词Domain adaptation (DA) pixel-level classification self-training triplet adversarial learning very high resolution (VHR)
ISSN号0196-2892
DOI10.1109/TGRS.2019.2958123
通讯作者Liu, Hongmin(hmliu_82@163.com)
英文摘要Pixel-level classification for very high resolution (VHR) images is a crucial but challenging task in remote sensing. However, since the diverse ways of satellite image acquisition and the distinct structures of various regions, the distributions of the same semantic classes among different data sets are dissimilar. Therefore, the classification model trained on one data set (source domain) may collapse, when it is directly applied to another one (target domain). To solve this problem, many adversarial-based domain adaptation methods have been proposed. However, these methods only consider the source and the target domains independently in the adversarial training, where only the target domain is explicitly contributed to narrow the gap between the distributions of both domains. Unlike previous methods, we propose a triplet adversarial domain adaptation (TriADA) method that jointly considers both domains to learn a domain-invariant classifier by a novel domain similarity discriminator. Specifically, the discriminator takes a triplet of segmentation maps as input, where two segmentation maps from the same domain are to be distinguished from the two maps from the different domains during the adversarial learning. Consequently, it explicitly considers both domains' information to narrow the distribution gap across domains. To enhance the discriminability of the classifier on the target domain, a class-aware self-training strategy, which depends on the output of the discriminator, is proposed to assign pseudo-labels with high adapted confidence on target data to retrain the classifier. Extensive experiments on several VHR pixel-level classification benchmarks demonstrate the effectiveness of our method as well as its superiority to the-state of the art.
资助项目Major Project for New Generation of Artificial Intelligence (AI)[2018AAA0100402] ; National Natural Science Foundation of China[61573352] ; National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[61620106003] ; National Natural Science Foundation of China[61773377] ; Young Elite Scientists Sponsorship Program by China Association for Science and Technology (CAST)[2018QNRC001]
WOS研究方向Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
语种英语
WOS记录号WOS:000529868700044
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Major Project for New Generation of Artificial Intelligence (AI) ; National Natural Science Foundation of China ; Young Elite Scientists Sponsorship Program by China Association for Science and Technology (CAST)
源URL[http://ir.ia.ac.cn/handle/173211/39401]  
专题自动化研究所_模式识别国家重点实验室_遥感图像处理团队
中国科学院自动化研究所
通讯作者Liu, Hongmin
作者单位1.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China
2.Henan Polytech Univ, Sch Comp Sci & Technol, Jiaozuo 454000, Henan, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Yan, Liang,Fan, Bin,Liu, Hongmin,et al. Triplet Adversarial Domain Adaptation for Pixel-Level Classification of VHR Remote Sensing Images[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2020,58(5):3558-3573.
APA Yan, Liang,Fan, Bin,Liu, Hongmin,Huo, Chunlei,Xiang, Shiming,&Pan, Chunhong.(2020).Triplet Adversarial Domain Adaptation for Pixel-Level Classification of VHR Remote Sensing Images.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,58(5),3558-3573.
MLA Yan, Liang,et al."Triplet Adversarial Domain Adaptation for Pixel-Level Classification of VHR Remote Sensing Images".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 58.5(2020):3558-3573.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。