Semi-Supervised Deep Metric Learning Networks for Classification of Polarimetric SAR Data
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....
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-05-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/10/1593 |
id |
doaj-614802fe2f6b473285b580859a59096d |
---|---|
record_format |
Article |
spelling |
doaj-614802fe2f6b473285b580859a59096d2020-11-25T02:15:29ZengMDPI AGRemote Sensing2072-42922020-05-01121593159310.3390/rs12101593Semi-Supervised Deep Metric Learning Networks for Classification of Polarimetric SAR DataHongying Liu0Ruyi Luo1Fanhua Shang2Xuechun Meng3Shuiping Gou4Biao Hou5Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaRecently, 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.https://www.mdpi.com/2072-4292/12/10/1593metric learningsemi-supervised classificationmanifold regularization |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hongying Liu Ruyi Luo Fanhua Shang Xuechun Meng Shuiping Gou Biao Hou |
spellingShingle |
Hongying Liu Ruyi Luo Fanhua Shang Xuechun Meng Shuiping Gou Biao Hou Semi-Supervised Deep Metric Learning Networks for Classification of Polarimetric SAR Data Remote Sensing metric learning semi-supervised classification manifold regularization |
author_facet |
Hongying Liu Ruyi Luo Fanhua Shang Xuechun Meng Shuiping Gou Biao Hou |
author_sort |
Hongying Liu |
title |
Semi-Supervised Deep Metric Learning Networks for Classification of Polarimetric SAR Data |
title_short |
Semi-Supervised Deep Metric Learning Networks for Classification of Polarimetric SAR Data |
title_full |
Semi-Supervised Deep Metric Learning Networks for Classification of Polarimetric SAR Data |
title_fullStr |
Semi-Supervised Deep Metric Learning Networks for Classification of Polarimetric SAR Data |
title_full_unstemmed |
Semi-Supervised Deep Metric Learning Networks for Classification of Polarimetric SAR Data |
title_sort |
semi-supervised deep metric learning networks for classification of polarimetric sar data |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2020-05-01 |
description |
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. |
topic |
metric learning semi-supervised classification manifold regularization |
url |
https://www.mdpi.com/2072-4292/12/10/1593 |
work_keys_str_mv |
AT hongyingliu semisuperviseddeepmetriclearningnetworksforclassificationofpolarimetricsardata AT ruyiluo semisuperviseddeepmetriclearningnetworksforclassificationofpolarimetricsardata AT fanhuashang semisuperviseddeepmetriclearningnetworksforclassificationofpolarimetricsardata AT xuechunmeng semisuperviseddeepmetriclearningnetworksforclassificationofpolarimetricsardata AT shuipinggou semisuperviseddeepmetriclearningnetworksforclassificationofpolarimetricsardata AT biaohou semisuperviseddeepmetriclearningnetworksforclassificationofpolarimetricsardata |
_version_ |
1724896054465265664 |