Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification
In this article, we propose a novelteacher–student-based label propagation deep semisupervised learning (TSLP-SSL) method for sea ice classification based on Sentinel-1 synthetic aperture radar data. For sea ice classification, labeling the data precisely is very time consuming and requir...
Published in: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
IEEE
2021
|
Subjects: | |
Online Access: | https://doi.org/10.1109/JSTARS.2021.3119485 https://doaj.org/article/8ed3ec0550f54b1185cfecd9e8ac5aca |
id |
ftdoajarticles:oai:doaj.org/article:8ed3ec0550f54b1185cfecd9e8ac5aca |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:8ed3ec0550f54b1185cfecd9e8ac5aca 2023-05-15T18:16:11+02:00 Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification Salman Khaleghian Habib Ullah Thomas Kraemer Torbjorn Eltoft Andrea Marinoni 2021-01-01T00:00:00Z https://doi.org/10.1109/JSTARS.2021.3119485 https://doaj.org/article/8ed3ec0550f54b1185cfecd9e8ac5aca EN eng IEEE https://ieeexplore.ieee.org/document/9573360/ https://doaj.org/toc/2151-1535 2151-1535 doi:10.1109/JSTARS.2021.3119485 https://doaj.org/article/8ed3ec0550f54b1185cfecd9e8ac5aca IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 10761-10772 (2021) Deep learning earth observation scarce training data sea ice classification semisupervised learning (SSL) Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 article 2021 ftdoajarticles https://doi.org/10.1109/JSTARS.2021.3119485 2022-12-31T10:23:53Z In this article, we propose a novelteacher–student-based label propagation deep semisupervised learning (TSLP-SSL) method for sea ice classification based on Sentinel-1 synthetic aperture radar data. For sea ice classification, labeling the data precisely is very time consuming and requires expert knowledge. Our method efficiently learns sea ice characteristics from a limited number of labeled samples and a relatively large number of unlabeled samples. Therefore, our method addresses the key challenge of using a limited number of precisely labeled samples to achieve generalization capability by discovering the underlying sea ice characteristics also from unlabeled data. We perform experimental analysis considering a standard dataset consisting of properly labeled sea ice data spanning over different time slots of the year. Both qualitative and quantitative results obtained on this dataset show that our proposed TSLP-SSL method outperforms deep supervised and semisupervised reference methods. Article in Journal/Newspaper Sea ice Directory of Open Access Journals: DOAJ Articles IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14 10761 10772 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Deep learning earth observation scarce training data sea ice classification semisupervised learning (SSL) Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 |
spellingShingle |
Deep learning earth observation scarce training data sea ice classification semisupervised learning (SSL) Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 Salman Khaleghian Habib Ullah Thomas Kraemer Torbjorn Eltoft Andrea Marinoni Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification |
topic_facet |
Deep learning earth observation scarce training data sea ice classification semisupervised learning (SSL) Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 |
description |
In this article, we propose a novelteacher–student-based label propagation deep semisupervised learning (TSLP-SSL) method for sea ice classification based on Sentinel-1 synthetic aperture radar data. For sea ice classification, labeling the data precisely is very time consuming and requires expert knowledge. Our method efficiently learns sea ice characteristics from a limited number of labeled samples and a relatively large number of unlabeled samples. Therefore, our method addresses the key challenge of using a limited number of precisely labeled samples to achieve generalization capability by discovering the underlying sea ice characteristics also from unlabeled data. We perform experimental analysis considering a standard dataset consisting of properly labeled sea ice data spanning over different time slots of the year. Both qualitative and quantitative results obtained on this dataset show that our proposed TSLP-SSL method outperforms deep supervised and semisupervised reference methods. |
format |
Article in Journal/Newspaper |
author |
Salman Khaleghian Habib Ullah Thomas Kraemer Torbjorn Eltoft Andrea Marinoni |
author_facet |
Salman Khaleghian Habib Ullah Thomas Kraemer Torbjorn Eltoft Andrea Marinoni |
author_sort |
Salman Khaleghian |
title |
Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification |
title_short |
Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification |
title_full |
Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification |
title_fullStr |
Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification |
title_full_unstemmed |
Deep Semisupervised Teacher–Student Model Based on Label Propagation for Sea Ice Classification |
title_sort |
deep semisupervised teacher–student model based on label propagation for sea ice classification |
publisher |
IEEE |
publishDate |
2021 |
url |
https://doi.org/10.1109/JSTARS.2021.3119485 https://doaj.org/article/8ed3ec0550f54b1185cfecd9e8ac5aca |
genre |
Sea ice |
genre_facet |
Sea ice |
op_source |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 10761-10772 (2021) |
op_relation |
https://ieeexplore.ieee.org/document/9573360/ https://doaj.org/toc/2151-1535 2151-1535 doi:10.1109/JSTARS.2021.3119485 https://doaj.org/article/8ed3ec0550f54b1185cfecd9e8ac5aca |
op_doi |
https://doi.org/10.1109/JSTARS.2021.3119485 |
container_title |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
container_volume |
14 |
container_start_page |
10761 |
op_container_end_page |
10772 |
_version_ |
1766189638587777024 |