遥感
计算机科学
人工智能
计算机视觉
高分辨率
分割
卫星
图像分割
图像分辨率
领域(数学分析)
地质学
地球观测
卫星图像
卫星图像
目标检测
分辨率(逻辑)
特征提取
图像处理
遥感应用
雷达成像
模式识别(心理学)
图像(数学)
作者
Yongqi Sun,Yujun Quan,Anzhu Yu,Yu Su,Xin Li,Chenguang Dai,Xuanguang Liu,Yanfei Zhong
标识
DOI:10.1109/tgrs.2026.3701909
摘要
Satellite remote sensing images exhibit significant cross-domain discrepancies due to variations in sensors, imaging conditions, and regional characteristics. These discrepancies degrade the performance of semantic segmentation models on unseen target domains. Unsupervised Domain Adaptation (UDA) mitigates this problem but requires target domain images during training. Achieving robust cross-domain generalization with foundation models typically relies on large-scale architectures, incurring substantial computational overhead that limits practical deployment. This paper introduces a novel perspective by leveraging zero-shot relative depth maps as domain-invariant geometric priors to guide cross-domain semantic segmentation of satellite remote sensing images. The proposed framework is compatible with most encoder-decoder architectures and makes three key contributions: 1) A unified depth-guided framework for optical remote sensing cross-domain segmentation. 2) A multi-scale contrastive learning module that aligns optical and relative depth features, enhancing optical feature representation. 3) A refinement strategy using shallow relative depth features to guide semantic mask prediction. Experiments across three cross-domain scenarios, including the LoveDA benchmark, a self-constructed circumpolar cross-seasonal dataset, and a cross=-dataset generalization setting, demonstrate that relative depth serves as an effective spatial prior. Notably, the proposed method achieves comparable or superior accuracy to state-of-the-art UDA approaches that require target-domain images during training, while operating under the stricter zero-shot domain generalization setting where no target data is accessible. The codes will be released at https://github.com/ArthasMil/DGCD.
科研通智能强力驱动
Strongly Powered by AbleSci AI