Self-Supervised Learning for Building Damage Assessment from Large-scale xBD Satellite Imagery Benchmark Datasets

TL;DR

This paper introduces a self-supervised learning approach using a novel asymmetric twin network architecture to improve building damage assessment from satellite imagery, reducing reliance on labeled data and outperforming baseline methods.

Contribution

It presents a new self-supervised comparative learning method and a novel network architecture for building damage assessment, addressing data labeling limitations.

Findings

Improved accuracy over baseline methods

Demonstrated potential of self-supervised learning in damage recognition

Effective on large-scale xBD dataset

Abstract

In the field of post-disaster assessment, for timely and accurate rescue and localization after a disaster, people need to know the location of damaged buildings. In deep learning, some scholars have proposed methods to make automatic and highly accurate building damage assessments by remote sensing images, which are proved to be more efficient than assessment by domain experts. However, due to the lack of a large amount of labeled data, these kinds of tasks can suffer from being able to do an accurate assessment, as the efficiency of deep learning models relies highly on labeled data. Although existing semi-supervised and unsupervised studies have made breakthroughs in this area, none of them has completely solved this problem. Therefore, we propose adopting a self-supervised comparative learning approach to address the task without the requirement of labeled data. We constructed a novel asymmetric twin network architecture and tested its performance on the xBD dataset. Experiment results of our model show the improvement compared to baseline and commonly used methods. We also demonstrated the potential of self-supervised methods for building damage recognition awareness.