Adapting Semi-Supervised Segmentation methods to Multimodal Remote Sensing Data

Remote sensing (RS) imagery is important for applications ranging from land cover and land use (LCLU) mapping to agriculture and forest monitoring. However, there is a limited availability of high-quality labeled data to use as a reference to train supervised learning (SL) models. Semi-supervised le...

Full description

Saved in:
Bibliographic Details
Main Authors: I. Hernandez-Sequeira, D. Ibanez, R. Fernandez-Beltran, F. Pla
Format: Article
Language:English
Published: Copernicus Publications 2025-05-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-M-7-2025/21/2025/isprs-archives-XLVIII-M-7-2025-21-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850270932233355264
author I. Hernandez-Sequeira
D. Ibanez
R. Fernandez-Beltran
F. Pla
author_facet I. Hernandez-Sequeira
D. Ibanez
R. Fernandez-Beltran
F. Pla
author_sort I. Hernandez-Sequeira
collection DOAJ
description Remote sensing (RS) imagery is important for applications ranging from land cover and land use (LCLU) mapping to agriculture and forest monitoring. However, there is a limited availability of high-quality labeled data to use as a reference to train supervised learning (SL) models. Semi-supervised learning (SSL) frameworks, such as UniMatch (Yang et al., 2023), use pseudo-labeling and consistency regularization methods to address this limitation. Similar works have been adapted to RS: LSST (Lu et al., 2022) refines pseudo-labels with adaptive class-specific thresholds, while RS-DWL (Huang et al., 2024) mitigates noise and class imbalance through decoupled learning and confidence-based weighting. Despite these advances, SSL applications to multimodal RS imagery remain underexplored. We address this gap by adapting the SSL framework UniMatch to incorporate diverse encoders and multimodal remote sensing data for LCLU segmentation. We experimented on FLAIR-2 (Garioud et al., 2023), a dataset that combines very high-resolution aerial imagery (RGB) with near-infrared (NIR) data and elevation measurements (above-ground height). Key findings reveal that we achieved the best segmentation results using a transformer encoder for SL and SSL scenarios. When comparing RGB-only data and multimodal data, we observed that some classes, like “buildings”, “water”, and “coniferous”, benefited from the inclusion of NIR and elevation information. In the semi-supervised experiments, where only half of the data was labeled, and the remaining half was used as unlabeled (simulating a real-world scenario), the multimodal SSL approach outperformed the fully supervised learning (FSL) approach using only the labeled subset (1/2). These results highlight the strong potential of data fusion in RS applications with limited labeled data.
format Article
id doaj-art-9de9e8d415654452b4a4d4ac9d735043
institution OA Journals
issn 1682-1750
2194-9034
language English
publishDate 2025-05-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-9de9e8d415654452b4a4d4ac9d7350432025-08-20T01:52:23ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342025-05-01XLVIII-M-7-2025212810.5194/isprs-archives-XLVIII-M-7-2025-21-2025Adapting Semi-Supervised Segmentation methods to Multimodal Remote Sensing DataI. Hernandez-Sequeira0D. Ibanez1R. Fernandez-Beltran2F. Pla3Institute of New Imaging Technologies, University Jaume I, 12071 Castellón de la Plana, SpainInstitute of New Imaging Technologies, University Jaume I, 12071 Castellón de la Plana, SpainDept. of Computer Science and Systems, University of Murcia, 30100 Murcia, SpainInstitute of New Imaging Technologies, University Jaume I, 12071 Castellón de la Plana, SpainRemote sensing (RS) imagery is important for applications ranging from land cover and land use (LCLU) mapping to agriculture and forest monitoring. However, there is a limited availability of high-quality labeled data to use as a reference to train supervised learning (SL) models. Semi-supervised learning (SSL) frameworks, such as UniMatch (Yang et al., 2023), use pseudo-labeling and consistency regularization methods to address this limitation. Similar works have been adapted to RS: LSST (Lu et al., 2022) refines pseudo-labels with adaptive class-specific thresholds, while RS-DWL (Huang et al., 2024) mitigates noise and class imbalance through decoupled learning and confidence-based weighting. Despite these advances, SSL applications to multimodal RS imagery remain underexplored. We address this gap by adapting the SSL framework UniMatch to incorporate diverse encoders and multimodal remote sensing data for LCLU segmentation. We experimented on FLAIR-2 (Garioud et al., 2023), a dataset that combines very high-resolution aerial imagery (RGB) with near-infrared (NIR) data and elevation measurements (above-ground height). Key findings reveal that we achieved the best segmentation results using a transformer encoder for SL and SSL scenarios. When comparing RGB-only data and multimodal data, we observed that some classes, like “buildings”, “water”, and “coniferous”, benefited from the inclusion of NIR and elevation information. In the semi-supervised experiments, where only half of the data was labeled, and the remaining half was used as unlabeled (simulating a real-world scenario), the multimodal SSL approach outperformed the fully supervised learning (FSL) approach using only the labeled subset (1/2). These results highlight the strong potential of data fusion in RS applications with limited labeled data.https://isprs-archives.copernicus.org/articles/XLVIII-M-7-2025/21/2025/isprs-archives-XLVIII-M-7-2025-21-2025.pdf
spellingShingle I. Hernandez-Sequeira
D. Ibanez
R. Fernandez-Beltran
F. Pla
Adapting Semi-Supervised Segmentation methods to Multimodal Remote Sensing Data
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Adapting Semi-Supervised Segmentation methods to Multimodal Remote Sensing Data
title_full Adapting Semi-Supervised Segmentation methods to Multimodal Remote Sensing Data
title_fullStr Adapting Semi-Supervised Segmentation methods to Multimodal Remote Sensing Data
title_full_unstemmed Adapting Semi-Supervised Segmentation methods to Multimodal Remote Sensing Data
title_short Adapting Semi-Supervised Segmentation methods to Multimodal Remote Sensing Data
title_sort adapting semi supervised segmentation methods to multimodal remote sensing data
url https://isprs-archives.copernicus.org/articles/XLVIII-M-7-2025/21/2025/isprs-archives-XLVIII-M-7-2025-21-2025.pdf
work_keys_str_mv AT ihernandezsequeira adaptingsemisupervisedsegmentationmethodstomultimodalremotesensingdata
AT dibanez adaptingsemisupervisedsegmentationmethodstomultimodalremotesensingdata
AT rfernandezbeltran adaptingsemisupervisedsegmentationmethodstomultimodalremotesensingdata
AT fpla adaptingsemisupervisedsegmentationmethodstomultimodalremotesensingdata