Learning Efficient Unsupervised Satellite Image-based Building Damage Detection

Zhang, Y; Wang, Z; Luo, Y; Yu, X; Huang, Z

Learning Efficient Unsupervised Satellite Image-based Building Damage Detection

Zhang, Y Wang, Z Luo, Y Yu, X

Huang, Z

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: Proceedings - IEEE International Conference on Data Mining, ICDM, 2024, 00, pp. 1547-1552
Issue Date:: 2024-01-01

Closed Access

	Filename	Description	Size
	1716008.pdf	Published version	422.14 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, Y
dc.contributor.author	Wang, Z
dc.contributor.author	Luo, Y
dc.contributor.author	Yu, X https://orcid.org/0000-0002-0269-5649
dc.contributor.author	Huang, Z
dc.contributor.editor	Chen, G
dc.contributor.editor	Khan, L
dc.contributor.editor	Gao, X
dc.contributor.editor	Qiu, M
dc.contributor.editor	Pedrycz, W
dc.contributor.editor	Wu, X
dc.date	2023-12-01
dc.date.accessioned	2024-08-07T05:05:12Z
dc.date.available	2024-08-07T05:05:12Z
dc.date.issued	2024-01-01
dc.identifier.citation	Proceedings - IEEE International Conference on Data Mining, ICDM, 2024, 00, pp. 1547-1552
dc.identifier.issn	1550-4786
dc.identifier.uri	http://hdl.handle.net/10453/180268
dc.description.abstract	Existing Building Damage Detection (BDD) methods always require labour-intensive pixel-level annotations of buildings and their conditions, hence largely limiting their applications. In this paper, we investigate a challenging yet practical scenario of BDD, Unsupervised Building Damage Detection (U-BDD), where only unlabelled pre- and post-disaster satellite image pairs are provided. As a pilot study, we have first proposed an advanced U-BDD baseline that leverages pre-trained vision-language foundation models to address the U-BDD task. However, the apparent domain gap between satellite and generic images causes low confidence in the foundation models used to identify buildings and their damages. In response, we further present a novel self-supervised framework, U-BDD++, which improves upon the U-BDD baseline by addressing domain-specific issues associated with satellite imagery. Extensive experiments on the widely used building damage assessment benchmark demonstrate the effectiveness of the proposed method for unsupervised building damage detection. The presented annotation-free and foundation model-based paradigm ensures an efficient learning phase. This study opens a new direction for real-world BDD and sets a strong baseline for future research.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	Proceedings - IEEE International Conference on Data Mining, ICDM
dc.relation.ispartof	IEEE International Conference on Data Mining
dc.relation.ispartofseries	IEEE International Conference on Data Mining
dc.relation.isbasedon	10.1109/ICDM58522.2023.00206
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Learning Efficient Unsupervised Satellite Image-based Building Damage Detection
dc.type	Conference Proceeding
utslib.citation.volume	00
utslib.location.activity	Shanghai, China
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2024-08-07T05:05:10Z
pubs.finish-date	2023-12-04
pubs.place-of-publication	Piscataway, USA
pubs.publication-status	Published
pubs.start-date	2023-12-01
pubs.volume	00
dc.location	Piscataway, USA

Abstract:

Existing Building Damage Detection (BDD) methods always require labour-intensive pixel-level annotations of buildings and their conditions, hence largely limiting their applications. In this paper, we investigate a challenging yet practical scenario of BDD, Unsupervised Building Damage Detection (U-BDD), where only unlabelled pre- and post-disaster satellite image pairs are provided. As a pilot study, we have first proposed an advanced U-BDD baseline that leverages pre-trained vision-language foundation models to address the U-BDD task. However, the apparent domain gap between satellite and generic images causes low confidence in the foundation models used to identify buildings and their damages. In response, we further present a novel self-supervised framework, U-BDD++, which improves upon the U-BDD baseline by addressing domain-specific issues associated with satellite imagery. Extensive experiments on the widely used building damage assessment benchmark demonstrate the effectiveness of the proposed method for unsupervised building damage detection. The presented annotation-free and foundation model-based paradigm ensures an efficient learning phase. This study opens a new direction for real-world BDD and sets a strong baseline for future research.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/180268