AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation

Ziyang Gong, Zhixiang Wei, Di Wang, Xiaoxing Hu, Xianzheng Ma, Hongruixuan Chen, Yuru Jia, Yupeng Deng, Zhenming Ji, Xiangwei Zhu, Xue Yang, Naoto Yokoya and 4 more

TPAMI 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation · 47 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add GSE module (ablation)Rein · CASID ablationavg mIoU: 59.2 -> 59.6Improved
add MIM decoder and loss (ablation)Rein · CASID ablationavg mIoU: 59.2 -> 60.4Improved
add Earth-Style Injection (ablation)Rein · CASID ablationavg mIoU: 59.2 -> 59.8Improved
combine GSE, MIM and Style (full CrossEarth) (ablation)Rein · CASID ablationavg mIoU: 59.2 -> 61.6Improved
use cross-attention injector instead of FFN (ablation)CrossEarth · CASID ablationavg mIoU: 61.2 -> 61.6Improved
use ASPP MIM decoder instead of linear (ablation)CrossEarth · CASID ablationavg mIoU: 59.1 -> 61.6Improved
lower style gate probability p from 0.9 to 0.1 (ablation)CrossEarth · CASID ablationavg mIoU: 58.7 -> 61.6Improved
use l1 instead of l2 for mask loss (ablation)CrossEarth · CASID ablationavg mIoU: 59.8 -> 61.6Improved
use l1 instead of l2 for delta loss (ablation)CrossEarth · CASID ablationavg mIoU: 60.5 -> 61.6Improved
CrossEarth instead of Rein on building extraction A2SRein · WHU Building A2SmIoU: 30.8 -> 44.3Improved
CrossEarth instead of Rein on A2S-IRein · WHU Building A2S-ImIoU: 48.0 -> 57.1Improved
CrossEarth instead of Rein on S2ARein · WHU Building S2AmIoU: 66.8 -> 64.5Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy