# CrossEarth-SAR: A SAR-Centric and Billion-Scale Geospatial Foundation Model for Domain Generalizable Semantic Segmentation

arXiv: https://arxiv.org/abs/2603.12008 · HTML: https://mlsanity.com/paper/2603.12008/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 68 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Builds on (most cited first, 30 of 30)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2207.08051/) (2022)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery](https://mlsanity.com/paper/2312.10115/) (2023)
- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (2022)
- [SEN12MS -- A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion](https://mlsanity.com/paper/1906.07789/) (2019)
- [Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2312.04265/) (2023)
- [OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping](https://mlsanity.com/paper/2210.10732/) (2022)
- [HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model](https://mlsanity.com/paper/2406.11519/) (2024)
- [MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining](https://mlsanity.com/paper/2403.13430/) (2024)
- [SSL4EO-L: Datasets and Foundation Models for Landsat Imagery](https://mlsanity.com/paper/2306.09424/) (2023)
- [SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection](https://mlsanity.com/paper/2403.06534/) (2024)
- [Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2311.15153/) (2023)
- [The QXS-SAROPT Dataset for Deep Learning in SAR-Optical Data Fusion](https://mlsanity.com/paper/2103.08259/) (2021)
- [CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2410.22629/) (2024)
- [SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing](https://mlsanity.com/paper/2507.13812/) (2025)
- [Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentation](https://mlsanity.com/paper/2505.06068/) (2025)
- [CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning](https://mlsanity.com/paper/2403.17369/) (2024)
- [ASANet: Asymmetric Semantic Aligning Network for RGB and SAR image land cover classification](https://mlsanity.com/paper/2412.02044/) (2024)
- [Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?](https://mlsanity.com/paper/2503.07890/) (2025)
- [The SARptical Dataset for Joint Analysis of SAR and Optical Image in Dense Urban Area](https://mlsanity.com/paper/1801.07532/) (2018)
- [Adaptively Distilled ControlNet: Accelerated Training and Superior Sampling for Medical Image Synthesis](https://mlsanity.com/paper/2507.23652/) (2025)
- [A review of deep-learning techniques for SAR image restoration](https://mlsanity.com/paper/2101.11852/) (2021)
- [A Complex-valued SAR Foundation Model Based on Physically Inspired Representation Learning](https://mlsanity.com/paper/2504.11999/) (2025)

## Built on by (most cited first, 4 of 4)

- [RemoteZero: Geospatial Reasoning with Zero Labels](https://mlsanity.com/paper/2605.04451/) (2026)
- [SARATR-X-v2: Scale-Aware Structural Pre-Training for SAR Foundation Models](https://mlsanity.com/paper/2607.23238/) (2026)
- [Earth Observation Foundation Models for Terrestrial Ecohydrology: From Representation Learning to Process Inference](https://mlsanity.com/paper/2608.15282/) (2026)
- [CETUS: How Far Do Representations Trained on Earth Transfer to Cassini SAR of Titan?](https://mlsanity.com/paper/2610.07576/) (2026)

## Abstract (arXiv)

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.