Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach

Accurate classification of building roof types from aerial imagery is crucial for various remote sensing applications, including urban planning, disaster management, and infrastructure monitoring. However, this task is often hindered by the limited availability of labeled data for supervised learnin...

Full description

Saved in:
Bibliographic Details
Main Authors: G. Mutreja, K. Bittner
Format: Article
Language:English
Published: Copernicus Publications 2025-07-01
Series:ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-annals.copernicus.org/articles/X-G-2025/591/2025/isprs-annals-X-G-2025-591-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849428792562417664
author G. Mutreja
K. Bittner
author_facet G. Mutreja
K. Bittner
author_sort G. Mutreja
collection DOAJ
description Accurate classification of building roof types from aerial imagery is crucial for various remote sensing applications, including urban planning, disaster management, and infrastructure monitoring. However, this task is often hindered by the limited availability of labeled data for supervised learning approaches. To address this challenge, this paper investigates the effectiveness of selfsupervised learning with EfficientNet architectures, known for their computational efficiency, for building roof type classification. We propose a novel framework that incorporates a Convolutional Block Attention Module (CBAM) to enhance the feature extraction capabilities of EfficientNet. Furthermore, we explore the benefits of pretraining on a domain-specific dataset, the Aerial Image Dataset (AID), compared to ImageNet pretraining. Our experimental results demonstrate the superiority of our approach. Employing Simple Framework for Contrastive Learning of Visual Representations (SimCLR) with EfficientNet-B3 and CBAM achieves a 95.5% accuracy on our validation set, matching the performance of state-of-the-art transformer-based models while utilizing significantly fewer parameters. We also provide a comprehensive evaluation on two challenging test sets, demonstrating the generalization capability of our method. Notably, our findings highlight the effectiveness of domain-specific pretraining, consistently leading to higher accuracy compared to models pretrained on the generic ImageNet dataset. Our work establishes EfficientNetbased self-supervised learning as a computationally efficient and highly effective approach for building roof type classification, particularly beneficial in scenarios with limited labeled data.
format Article
id doaj-art-3b352ee209164a3c8ff5e2e7dbb054b3
institution Kabale University
issn 2194-9042
2194-9050
language English
publishDate 2025-07-01
publisher Copernicus Publications
record_format Article
series ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-3b352ee209164a3c8ff5e2e7dbb054b32025-08-20T03:28:34ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502025-07-01X-G-202559159710.5194/isprs-annals-X-G-2025-591-2025Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised ApproachG. Mutreja0K. Bittner1Remote Sensing Technology Institute, German Aerospace Center (DLR), Weßling, GermanyRemote Sensing Technology Institute, German Aerospace Center (DLR), Weßling, GermanyAccurate classification of building roof types from aerial imagery is crucial for various remote sensing applications, including urban planning, disaster management, and infrastructure monitoring. However, this task is often hindered by the limited availability of labeled data for supervised learning approaches. To address this challenge, this paper investigates the effectiveness of selfsupervised learning with EfficientNet architectures, known for their computational efficiency, for building roof type classification. We propose a novel framework that incorporates a Convolutional Block Attention Module (CBAM) to enhance the feature extraction capabilities of EfficientNet. Furthermore, we explore the benefits of pretraining on a domain-specific dataset, the Aerial Image Dataset (AID), compared to ImageNet pretraining. Our experimental results demonstrate the superiority of our approach. Employing Simple Framework for Contrastive Learning of Visual Representations (SimCLR) with EfficientNet-B3 and CBAM achieves a 95.5% accuracy on our validation set, matching the performance of state-of-the-art transformer-based models while utilizing significantly fewer parameters. We also provide a comprehensive evaluation on two challenging test sets, demonstrating the generalization capability of our method. Notably, our findings highlight the effectiveness of domain-specific pretraining, consistently leading to higher accuracy compared to models pretrained on the generic ImageNet dataset. Our work establishes EfficientNetbased self-supervised learning as a computationally efficient and highly effective approach for building roof type classification, particularly beneficial in scenarios with limited labeled data.https://isprs-annals.copernicus.org/articles/X-G-2025/591/2025/isprs-annals-X-G-2025-591-2025.pdf
spellingShingle G. Mutreja
K. Bittner
Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach
title_full Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach
title_fullStr Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach
title_full_unstemmed Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach
title_short Efficient Building Roof Type Classification: A Domain-Specific Self-Supervised Approach
title_sort efficient building roof type classification a domain specific self supervised approach
url https://isprs-annals.copernicus.org/articles/X-G-2025/591/2025/isprs-annals-X-G-2025-591-2025.pdf
work_keys_str_mv AT gmutreja efficientbuildingrooftypeclassificationadomainspecificselfsupervisedapproach
AT kbittner efficientbuildingrooftypeclassificationadomainspecificselfsupervisedapproach