Saved in:
Bibliographic Details
Main Authors: Yaghmour, Anan, Crawford, Melba M., Prasad, Saurabh
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.01558
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912358616530944
author Yaghmour, Anan
Crawford, Melba M.
Prasad, Saurabh
author_facet Yaghmour, Anan
Crawford, Melba M.
Prasad, Saurabh
contents Remote sensing enables a wide range of critical applications such as land cover and land use mapping, crop yield prediction, and environmental monitoring. Advances in satellite technology have expanded remote sensing datasets, yet high-performance 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 pseudo-labeling with source-to-target generative pre-training. We further provide new mathematical insights into 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_01558
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Sensor Agnostic Domain Generalization Framework for Leveraging Geospatial Foundation Models: Enhancing Semantic Segmentation viaSynergistic Pseudo-Labeling and Generative Learning
Yaghmour, Anan
Crawford, Melba M.
Prasad, Saurabh
Computer Vision and Pattern Recognition
Remote sensing enables a wide range of critical applications such as land cover and land use mapping, crop yield prediction, and environmental monitoring. Advances in satellite technology have expanded remote sensing datasets, yet high-performance 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 pseudo-labeling with source-to-target generative pre-training. We further provide new mathematical insights into 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.
title A Sensor Agnostic Domain Generalization Framework for Leveraging Geospatial Foundation Models: Enhancing Semantic Segmentation viaSynergistic Pseudo-Labeling and Generative Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.01558