CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cao, Shilei, Gong, Ziyang, Lin, Hehai, Liu, Yang, Cheng, Jiashun, Hu, Xiaoxing, Liang, Haoyuan, Li, Guowen, Qin, Chengwei, Cheng, Hong, Yang, Xue, Zheng, Juepeng, Fu, Haohuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909926480150528
author Cao, Shilei
Gong, Ziyang
Lin, Hehai
Liu, Yang
Cheng, Jiashun
Hu, Xiaoxing
Liang, Haoyuan
Li, Guowen
Qin, Chengwei
Cheng, Hong
Yang, Xue
Zheng, Juepeng
Fu, Haohuan
author_facet Cao, Shilei
Gong, Ziyang
Lin, Hehai
Liu, Yang
Cheng, Jiashun
Hu, Xiaoxing
Liang, Haoyuan
Li, Guowen
Qin, Chengwei
Cheng, Hong
Yang, Xue
Zheng, Juepeng
Fu, Haohuan
contents In Remote Sensing (RS), Parameter-Efficient Fine-Tuning (PEFT) has emerged as a key approach to activate the generalizable representation ability of foundation models for downstream tasks. However, existing specialized PEFT methods often fail when applied to large-scale Earth observation tasks, as they are unable to fully handle the multifaceted and unpredictable domain gaps (\eg, spatial, semantic, and frequency shifts) inherent in RS data. To overcome this, we propose CrossEarth-Gate, which introduces two primary contributions. First, we establish a comprehensive RS module toolbox to address multifaceted domain gaps, comprising spatial, semantic, and frequency modules. Second, we develop a Fisher-guided adaptive selection mechanism that operates on this toolbox. This selection is guided by Fisher Information to quantify each module's importance by measuring its contribution to the task-specific gradient flow. It dynamically activates only the most critical modules at the appropriate layers, guiding the gradient flow to maximize adaptation effectiveness and efficiency. Comprehensive experiments validate the efficacy and generalizability of our method, where CrossEarth-Gate achieves state-of-the-art performance across 16 cross-domain benchmarks for RS semantic segmentation. The code of the work will be released.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20302
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation
Cao, Shilei
Gong, Ziyang
Lin, Hehai
Liu, Yang
Cheng, Jiashun
Hu, Xiaoxing
Liang, Haoyuan
Li, Guowen
Qin, Chengwei
Cheng, Hong
Yang, Xue
Zheng, Juepeng
Fu, Haohuan
Computer Vision and Pattern Recognition
In Remote Sensing (RS), Parameter-Efficient Fine-Tuning (PEFT) has emerged as a key approach to activate the generalizable representation ability of foundation models for downstream tasks. However, existing specialized PEFT methods often fail when applied to large-scale Earth observation tasks, as they are unable to fully handle the multifaceted and unpredictable domain gaps (\eg, spatial, semantic, and frequency shifts) inherent in RS data. To overcome this, we propose CrossEarth-Gate, which introduces two primary contributions. First, we establish a comprehensive RS module toolbox to address multifaceted domain gaps, comprising spatial, semantic, and frequency modules. Second, we develop a Fisher-guided adaptive selection mechanism that operates on this toolbox. This selection is guided by Fisher Information to quantify each module's importance by measuring its contribution to the task-specific gradient flow. It dynamically activates only the most critical modules at the appropriate layers, guiding the gradient flow to maximize adaptation effectiveness and efficiency. Comprehensive experiments validate the efficacy and generalizability of our method, where CrossEarth-Gate achieves state-of-the-art performance across 16 cross-domain benchmarks for RS semantic segmentation. The code of the work will be released.
title CrossEarth-Gate: Fisher-Guided Adaptive Tuning Engine for Efficient Adaptation of Cross-Domain Remote Sensing Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.20302