Can I read Learning Efficient Unsupervised Satellite Image-based Building Damage Detection on EtoBox?

Learning Efficient Unsupervised Satellite Image-based Building Damage Detection by Zhang, Yiyun; Wang, Zijian; Luo, Yadan; Yu, Xin; Huang, Zi is a scholarly article available to read on EtoBox.

What is Learning Efficient Unsupervised Satellite Image-based Building Damage Detection about?

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 (i.e., Grounding DINO, SAM and CLIP) 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. Furthermore, the new Building Proposal Generation (BPG) module and the CLIP-enabled noisy Building Proposal Selection (CLIP-BPS) module in U-BDD++ ensure high-quality self-training. Extensive experiments on the widely used building damage assessment benchmark demonstrat

Author

Zhang, Yiyun; Wang, Zijian; Luo, Yadan; Yu, Xin; Huang, Zi

Published

2023

Language

EN