Saved in:
Bibliographic Details
Main Authors: Ye, Ziqi, Gong, Ziyang, Liao, Ning, Hu, Xiaoxing, Wang, Di, Chen, Hongruixuan, Huang, Chen, He, Yiguo, Jia, Yuru, Wang, Xiaoxing, Wang, Haipeng, Yang, Xue, Yan, Junchi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.12008
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912963396370432
author Ye, Ziqi
Gong, Ziyang
Liao, Ning
Hu, Xiaoxing
Wang, Di
Chen, Hongruixuan
Huang, Chen
He, Yiguo
Jia, Yuru
Wang, Xiaoxing
Wang, Haipeng
Yang, Xue
Yan, Junchi
author_facet Ye, Ziqi
Gong, Ziyang
Liao, Ning
Hu, Xiaoxing
Wang, Di
Chen, Hongruixuan
Huang, Chen
He, Yiguo
Jia, Yuru
Wang, Xiaoxing
Wang, Haipeng
Yang, Xue
Yan, Junchi
contents Synthetic Aperture Radar (SAR) enables global, all-weather earth observation. However, owing to diverse imaging mechanisms, domain shifts across sensors and regions severely hinder its semantic generalization. To address this, we present CrossEarth-SAR, the first billion-scale SAR vision foundation model built upon a novel physics-guided sparse mixture-of-experts (MoE) architecture incorporating physical descriptors, explicitly designed for cross-domain semantic segmentation. To facilitate large-scale pre-training, we develop CrossEarth-SAR-200K, a weakly and fully supervised dataset that unifies public and private SAR imagery. We also introduce a benchmark suite comprising 22 sub-benchmarks across 8 distinct domain gaps, establishing the first unified standard for domain generalization semantic segmentation on SAR imagery. Extensive experiments demonstrate that CrossEarth-SAR achieves state-of-the-art results on 20 benchmarks, surpassing previous methods by over 10\% mIoU on some benchmarks under multi-gap transfer. All code, benchmark and datasets will be publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2603_12008
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CrossEarth-SAR: A SAR-Centric and Billion-Scale Geospatial Foundation Model for Domain Generalizable Semantic Segmentation
Ye, Ziqi
Gong, Ziyang
Liao, Ning
Hu, Xiaoxing
Wang, Di
Chen, Hongruixuan
Huang, Chen
He, Yiguo
Jia, Yuru
Wang, Xiaoxing
Wang, Haipeng
Yang, Xue
Yan, Junchi
Computer Vision and Pattern Recognition
Synthetic Aperture Radar (SAR) enables global, all-weather earth observation. However, owing to diverse imaging mechanisms, domain shifts across sensors and regions severely hinder its semantic generalization. To address this, we present CrossEarth-SAR, the first billion-scale SAR vision foundation model built upon a novel physics-guided sparse mixture-of-experts (MoE) architecture incorporating physical descriptors, explicitly designed for cross-domain semantic segmentation. To facilitate large-scale pre-training, we develop CrossEarth-SAR-200K, a weakly and fully supervised dataset that unifies public and private SAR imagery. We also introduce a benchmark suite comprising 22 sub-benchmarks across 8 distinct domain gaps, establishing the first unified standard for domain generalization semantic segmentation on SAR imagery. Extensive experiments demonstrate that CrossEarth-SAR achieves state-of-the-art results on 20 benchmarks, surpassing previous methods by over 10\% mIoU on some benchmarks under multi-gap transfer. All code, benchmark and datasets will be publicly available.
title CrossEarth-SAR: A SAR-Centric and Billion-Scale Geospatial Foundation Model for Domain Generalizable Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.12008