AAAI 2026technical0 citations
Earth-Adapter: Bridge the Geospatial Domain Gaps with a Frequency-Guided Mixture of Adapters
Xiaoxing Hu, Ziyang Gong, Yupei Wang, Yuru Jia, Fei Lin, Dexiang Gao, Ke An, Jianhong Han
Abstract
Vision Foundation Models (VFMs), while powerful, often struggle in Remote Sensing (RS) segmentation tasks when combined with existing Parameter-Efficient Fine-Tuning (PEFT) methods. We observe that this limitation primarily arises from their inability to effectively handle the pervasive artifacts in RS imagery. To address this, we introduce Earth-Adapter, the first PEFT method specifically designed for RS artifact mitigation. Earth-Adapter introduces a novel Frequency-Guided Mixture of Adapters (MoA) approach, structured around a
BibTeX
@inproceedings{aaai2026_earthadapterbrid,
title = {Earth-Adapter: Bridge the Geospatial Domain Gaps with a Frequency-Guided Mixture of Adapters},
author = {Xiaoxing Hu and Ziyang Gong and Yupei Wang and Yuru Jia and Fei Lin and Dexiang Gao and Ke An and Jianhong Han and Zhuoran Sun and Gen Luo and Xue Yang},
booktitle = {AAAI 2026},
year = {2026}
}