Advancing Self-Supervised Learning for Building Change Detection and Damage Assessment: Unified Denoising Autoencoder and Contrastive Learning Framework

Building change detection and building damage assessment are two essential tasks in post-disaster analysis. Building change detection focuses on identifying changed building areas between bi-temporal images, while building damage assessment involves segmenting all buildings and classifying their dam...

Full description

Saved in:
Bibliographic Details
Main Authors: Songxi Yang, Bo Peng, Tang Sui, Meiliu Wu, Qunying Huang
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/15/2717
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849239568564355072
author Songxi Yang
Bo Peng
Tang Sui
Meiliu Wu
Qunying Huang
author_facet Songxi Yang
Bo Peng
Tang Sui
Meiliu Wu
Qunying Huang
author_sort Songxi Yang
collection DOAJ
description Building change detection and building damage assessment are two essential tasks in post-disaster analysis. Building change detection focuses on identifying changed building areas between bi-temporal images, while building damage assessment involves segmenting all buildings and classifying their damage severity. These tasks play a critical role in disaster response and urban development monitoring. Although supervised learning has significantly advanced building change detection and damage assessment, its reliance on large labeled datasets remains a major limitation. In contrast, self-supervised learning enables the extraction of meaningful data representations without explicit training labels. To address this challenge, we propose a self-supervised learning approach that unifies denoising autoencoders and contrastive learning, enabling effective data representation for building change detection and damage assessment. The proposed architecture integrates a dual denoising autoencoder with a Vision Transformer backbone and contrastive learning strategy, complemented by a Feature Pyramid Network-ResNet dual decoder and an Edge Guidance Module. This design enhances multi-scale feature extraction and enables edge-aware segmentation for accurate predictions. Extensive experiments were conducted on five public datasets, including xBD, LEVIR, LEVIR+, SYSU, and WHU, to evaluate the performance and generalization capabilities of the model. The results demonstrate that the proposed Denoising AutoEncoder-enhanced Dual-Fusion Network (DAEDFN) approach achieves competitive performance compared with fully supervised methods. On the xBD dataset, the largest dataset for building damage assessment, our proposed method achieves an F1 score of 0.892 for building segmentation, outperforming state-of-the-art methods. For building damage severity classification, the model achieves an F1 score of 0.632. On the building change detection datasets, the proposed method achieves F1 scores of 0.837 (LEVIR), 0.817 (LEVIR+), 0.768 (SYSU), and 0.876 (WHU), demonstrating model generalization across diverse scenarios. Despite these promising results, challenges remain in complex urban environments, small-scale changes, and fine-grained boundary detection. These findings highlight the potential of self-supervised learning in building change detection and damage assessment tasks.
format Article
id doaj-art-1cc557a51c8444efa74251a8ff67b489
institution Kabale University
issn 2072-4292
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-1cc557a51c8444efa74251a8ff67b4892025-08-20T04:00:55ZengMDPI AGRemote Sensing2072-42922025-08-011715271710.3390/rs17152717Advancing Self-Supervised Learning for Building Change Detection and Damage Assessment: Unified Denoising Autoencoder and Contrastive Learning FrameworkSongxi Yang0Bo Peng1Tang Sui2Meiliu Wu3Qunying Huang4Department of Geography, University of Wisconsin-Madison, Madison, WI 53705, USAPAII, Palo Alto, CA 94306, USADepartment of Geography, University of Wisconsin-Madison, Madison, WI 53705, USASchool of Geographical and Earth Sciences, University of Glasgow, Glasgow G12 8QQ, UKDepartment of Geography, University of Wisconsin-Madison, Madison, WI 53705, USABuilding change detection and building damage assessment are two essential tasks in post-disaster analysis. Building change detection focuses on identifying changed building areas between bi-temporal images, while building damage assessment involves segmenting all buildings and classifying their damage severity. These tasks play a critical role in disaster response and urban development monitoring. Although supervised learning has significantly advanced building change detection and damage assessment, its reliance on large labeled datasets remains a major limitation. In contrast, self-supervised learning enables the extraction of meaningful data representations without explicit training labels. To address this challenge, we propose a self-supervised learning approach that unifies denoising autoencoders and contrastive learning, enabling effective data representation for building change detection and damage assessment. The proposed architecture integrates a dual denoising autoencoder with a Vision Transformer backbone and contrastive learning strategy, complemented by a Feature Pyramid Network-ResNet dual decoder and an Edge Guidance Module. This design enhances multi-scale feature extraction and enables edge-aware segmentation for accurate predictions. Extensive experiments were conducted on five public datasets, including xBD, LEVIR, LEVIR+, SYSU, and WHU, to evaluate the performance and generalization capabilities of the model. The results demonstrate that the proposed Denoising AutoEncoder-enhanced Dual-Fusion Network (DAEDFN) approach achieves competitive performance compared with fully supervised methods. On the xBD dataset, the largest dataset for building damage assessment, our proposed method achieves an F1 score of 0.892 for building segmentation, outperforming state-of-the-art methods. For building damage severity classification, the model achieves an F1 score of 0.632. On the building change detection datasets, the proposed method achieves F1 scores of 0.837 (LEVIR), 0.817 (LEVIR+), 0.768 (SYSU), and 0.876 (WHU), demonstrating model generalization across diverse scenarios. Despite these promising results, challenges remain in complex urban environments, small-scale changes, and fine-grained boundary detection. These findings highlight the potential of self-supervised learning in building change detection and damage assessment tasks.https://www.mdpi.com/2072-4292/17/15/2717remote sensingchange detectiondamage assessmentself-supervised learningcontrastive learningvision transformer
spellingShingle Songxi Yang
Bo Peng
Tang Sui
Meiliu Wu
Qunying Huang
Advancing Self-Supervised Learning for Building Change Detection and Damage Assessment: Unified Denoising Autoencoder and Contrastive Learning Framework
Remote Sensing
remote sensing
change detection
damage assessment
self-supervised learning
contrastive learning
vision transformer
title Advancing Self-Supervised Learning for Building Change Detection and Damage Assessment: Unified Denoising Autoencoder and Contrastive Learning Framework
title_full Advancing Self-Supervised Learning for Building Change Detection and Damage Assessment: Unified Denoising Autoencoder and Contrastive Learning Framework
title_fullStr Advancing Self-Supervised Learning for Building Change Detection and Damage Assessment: Unified Denoising Autoencoder and Contrastive Learning Framework
title_full_unstemmed Advancing Self-Supervised Learning for Building Change Detection and Damage Assessment: Unified Denoising Autoencoder and Contrastive Learning Framework
title_short Advancing Self-Supervised Learning for Building Change Detection and Damage Assessment: Unified Denoising Autoencoder and Contrastive Learning Framework
title_sort advancing self supervised learning for building change detection and damage assessment unified denoising autoencoder and contrastive learning framework
topic remote sensing
change detection
damage assessment
self-supervised learning
contrastive learning
vision transformer
url https://www.mdpi.com/2072-4292/17/15/2717
work_keys_str_mv AT songxiyang advancingselfsupervisedlearningforbuildingchangedetectionanddamageassessmentunifieddenoisingautoencoderandcontrastivelearningframework
AT bopeng advancingselfsupervisedlearningforbuildingchangedetectionanddamageassessmentunifieddenoisingautoencoderandcontrastivelearningframework
AT tangsui advancingselfsupervisedlearningforbuildingchangedetectionanddamageassessmentunifieddenoisingautoencoderandcontrastivelearningframework
AT meiliuwu advancingselfsupervisedlearningforbuildingchangedetectionanddamageassessmentunifieddenoisingautoencoderandcontrastivelearningframework
AT qunyinghuang advancingselfsupervisedlearningforbuildingchangedetectionanddamageassessmentunifieddenoisingautoencoderandcontrastivelearningframework