A Sensor Agnostic Domain Generalization Framework for Leveraging Geospatial Foundation Models: Enhancing Semantic Segmentation viaSynergistic Pseudo-Labeling and Generative Learning

Remote sensing enables a wide range of critical applications such as land cover, land use mapping, crop yield prediction, and environmental monitoring. Advances in satellite technology have expanded RS datasets, yet highperformance segmentation models remain dependent on extensive labeled data-challenged by annotation scarcity and variability across sensors, illumination, and geography. Domain adaptation offers a promising solution to improve model generalization. This paper introduces a domain generalization approach to leveraging emerging geospatial foundation models, by combining soft-alignment pseudolabeling with source-to-target generative pre-training. We further provide new mathematical insights of MAE-based generative learning for domain-invariant feature learning. Experiments with hyperspectral and multispectral remote sensing datasets confirm our method's effectiveness in enhancing adaptability and segmentation performance 11Code available at: https://github.com/anan0110692/GeoAI-FoundGen.