Semi-Supervised Deep Metric Learning Networks for Classification of Polarimetric SAR Data

被引:6
|
作者
Liu, Hongying [1 ]
Luo, Ruyi [1 ]
Shang, Fanhua [1 ]
Meng, Xuechun [1 ]
Gou, Shuiping [1 ]
Hou, Biao [1 ]
机构
[1] Xidian Univ, Sch Artificial Intelligence, Minist Educ, Key Lab Intelligent Percept & Image Understanding, Xian 710071, Peoples R China
基金
中国国家自然科学基金;
关键词
metric learning; semi-supervised classification; manifold regularization;
D O I
10.3390/rs12101593
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Recently, classification methods based on deep learning have attained sound results for the classification of Polarimetric synthetic aperture radar (PolSAR) data. However, they generally require a great deal of labeled data to train their models, which limits their potential real-world applications. This paper proposes a novel semi-supervised deep metric learning network (SSDMLN) for feature learning and classification of PolSAR data. Inspired by distance metric learning, we construct a network, which transforms the linear mapping of metric learning into the non-linear projection in the layer-by-layer learning. With the prior knowledge of the sample categories, the network also learns a distance metric under which all pairs of similarly labeled samples are closer and dissimilar samples have larger relative distances. Moreover, we introduce a new manifold regularization to reduce the distance between neighboring samples since they are more likely to be homogeneous. The categorizing is achieved by using a simple classifier. Several experiments on both synthetic and real-world PolSAR data from different sensors are conducted and they demonstrate the effectiveness of SSDMLN with limited labeled samples, and SSDMLN is superior to state-of-the-art methods.
引用
收藏
页数:14
相关论文
共 50 条
  • [1] SEMI-SUPERVISED LEARNING FOR CLASSIFICATION OF POLARIMETRIC SAR-DATA
    Haensch, R.
    Hellwich, O.
    [J]. 2009 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-5, 2009, : 2289 - 2292
  • [2] Semi-Supervised Learning for Ill-Posed Polarimetric SAR Classification
    Uhlmann, Stefan
    Kiranyaz, Serkan
    Gabbouj, Moncef
    [J]. REMOTE SENSING, 2014, 6 (06) : 4801 - 4830
  • [3] Semi-supervised Metric Learning for Image Classification
    Hu, Jiwei
    Sun, ChenSheng
    Kin Man Lam
    [J]. ADVANCES IN MULTIMEDIA INFORMATION PROCESSING-PCM 2010, PT II, 2010, 6298 : 728 - 735
  • [4] Semi-supervised Clustering with Deep Metric Learning
    Li, Xiaocui
    Yin, Hongzhi
    Zhou, Ke
    Chen, Hongxu
    Sadiq, Shazia
    Zhou, Xiaofang
    [J]. DATABASE SYSTEMS FOR ADVANCED APPLICATIONS, 2019, 11448 : 383 - 386
  • [5] Semi-Supervised Metric Learning: A Deep Resurrection
    Dutta, Ujjal Kr
    Harandi, Mehrtash
    Sekhar, Chellu Chandra
    [J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 7279 - 7287
  • [6] Large Polarimetric SAR Data Semi-Supervised Classification With Spatial-Anchor Graph
    Liu, Hongying
    Wang, Yikai
    Yang, Shuyuan
    Wang, Shuang
    Feng, Jie
    Jiao, Licheng
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2016, 9 (04) : 1439 - 1458
  • [7] A Semi-Supervised Dimension Reduction Method for Polarimetric SAR Image Classification
    Xie Xinfang
    Xu Xin
    Dong Hao
    Wu Han
    Li Luoru
    [J]. ACTA OPTICA SINICA, 2018, 38 (04)
  • [8] SEMI-SUPERVISED CLASSIFICATION BASED ON ANCHOR-SPATIAL GRAPH FOR LARGE POLARIMETRIC SAR DATA
    Liu, Hongying
    Wang, Yikai
    Zhu, Dexiang
    Yang, Shuyuan
    Wang, Shuang
    Hon, Biao
    Jiao, Licheng
    [J]. 2015 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2015, : 1845 - 1848
  • [9] Metric learning by similarity network for deep semi-supervised learning
    Wu, Sanyou
    Feng, Xingdong
    Zhou, Fan
    [J]. DEVELOPMENTS OF ARTIFICIAL INTELLIGENCE TECHNOLOGIES IN COMPUTATION AND ROBOTICS, 2020, 12 : 995 - 1002
  • [10] Deep graph learning for semi-supervised classification
    Lin, Guangfeng
    Kang, Xiaobing
    Liao, Kaiyang
    Zhao, Fan
    Chen, Yajun
    [J]. PATTERN RECOGNITION, 2021, 118