Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data

TL;DR

This paper introduces a novel approach using text-to-image generative models to create synthetic data for improving the robustness of disaster damage assessment from aerial imagery, especially in low-resource domains.

Contribution

It proposes a scalable pipeline for generating synthetic post-disaster images and a two-stage training method to enhance model robustness across different domains.

Findings

Significant performance improvements in cross-domain damage assessment.

Effective synthetic data generation from low-resource domains.

Enhanced robustness of models in under-resourced geographies.

Abstract

We present a simple and efficient method to leverage emerging text-to-image generative models in creating large-scale synthetic supervision for the task of damage assessment from aerial images. While significant recent advances have resulted in improved techniques for damage assessment using aerial or satellite imagery, they still suffer from poor robustness to domains where manual labeled data is unavailable, directly impacting post-disaster humanitarian assistance in such under-resourced geographies. Our contribution towards improving domain robustness in this scenario is two-fold. Firstly, we leverage the text-guided mask-based image editing capabilities of generative models and build an efficient and easily scalable pipeline to generate thousands of post-disaster images from low-resource domains. Secondly, we propose a simple two-stage training approach to train robust models while using manual supervision from different source domains along with the generated synthetic target domain data. We validate the strength of our proposed framework under cross-geography domain transfer setting from xBD and SKAI images in both single-source and multi-source settings, achieving significant improvements over a source-only baseline in each case.