2024/05/30 by Edoardo Arnaudo, Arnaudo, Edoardo, Jacopo Lungo Vaschetti +11 · 2 citations
Computer Science · Engineering · #Advanced Computational Techniques and Applications #Automated Road and Building Extraction #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Remote-Sensing Image Classification
paper · pdf · doi:10.48550/arxiv.2405.20109
openalex publication_date 2024/05/30 · openalex created_date 2024/06/01 · openalex updated_date 2026/07/28
Very-High Resolution (VHR) remote sensing imagery is increasingly accessible, but often lacks annotations for effective machine learning applications. Recent foundation models like GroundingDINO and Segment Anything (SAM) provide opportunities to automatically generate annotations. This study introduces FMARS (Foundation Model Annotations in Remote Sensing), a methodology leveraging VHR imagery and foundation models for fast and robust annotation. We focus on disaster management and provide a large-scale dataset with labels obtained from pre-event imagery over 19 disaster events, derived from the Maxar Open Data initiative. We train segmentation models on the generated labels, using Unsupervised Domain Adaptation (UDA) techniques to increase transferability to real-world scenarios. Our results demonstrate the effectiveness of leveraging foundation models to automatically annotate remote sensing data at scale, enabling robust downstream models for critical applications. Code and dataset are available at \urlhttps://github.com/links-ads/igarss-fmars.