arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2611.03382cs.CV
收藏

ASCoR:面向遥感领域泛化的非对称语义-空间学习

ASCoR: Asymmetric Semantic-Spatial Learning for Remote Sensing Domain Generalization

Beihang University(北京航空航天大学);University of Science and Technology Beijing(北京科技大学);University of Liverpool(利物浦大学);Guangdong Electronic Information Engineering Research Institute, University of Electronic Science and Technology of China(电子科技大学广东电子信息工程研究院)

Zitong Wang, Shuchang Lyu, Meng Li, Qiang Wang, Guangliang Cheng, Zhenwei Shi

AI总结:

提出基于SAM3的非对称语义-空间框架ASCoR,通过双分支设计与可靠性路由器实现遥感领域泛化,在多基准跨域任务中取得最优性能。

摘要:

仅源域的遥感语义分割领域泛化(DG)旨在训练时无需目标域数据即可在未见域中获得可靠预测。尽管视觉基础模型提供可迁移知识,但类别识别仍对源域特定视觉线索敏感,而特定任务适配可能削弱预训练的可迁移性。我们提出ASCoR,这是一个基于SAM3的非对称语义-空间框架。其文本条件语义分支使用类别名称提示提供明确的类别指导;Probe-Once动态自适应LoRA将固定的适配预算分配到编码器块,以限制源域特定的专业化;互补的特定任务密集分支使用单独的冻结SAM3图像编码器学习多尺度空间表示;轻量可靠性路由器基于局部预测可靠性,通过有界空间校正整合两个分支。所有组件仅使用源域监督训练。在ISPRS、LoveDA和OpenEarthMap基准上的实验覆盖9种跨域迁移,ASCoR在6种ISPRS迁移中达到68.61%的先进平均IoU,比之前最优方法高2.69个百分点;在全部3种LoveDA/OpenEarthMap迁移中也取得最优结果,在乡村到城市、城市到乡村、城市到OpenEarthMap任务上的mIoU分别为59.07%、47.95%和49.38%。消融研究、特征可视化和空间可靠性分析验证了所提组件的有效性与互补性。代码:this https URL。

英文摘要:

Source-only domain generalization (DG) for remote sensing semantic segmentation seeks reliable predictions in unseen domains without target-domain data during training. Although vision foundation models offer transferable knowledge, category recognition remains sensitive to source-specific visual cues, while task-specific adaptation may weaken pretrained transferability. We propose ASCoR, an asymmetric semantic-spatial framework built on SAM3. Its text-conditioned semantic branch uses class-name prompts to provide explicit category guidance. Probe-Once Dynamic Adaptive LoRA distributes a fixed adaptation budget across encoder blocks to limit source-specific specialization. A complementary task-specific dense branch learns multi-scale spatial representations using a separate frozen SAM3 image encoder. A lightweight reliability router integrates the two branches through bounded spatial correction based on local prediction reliability. All components are trained using source-domain supervision only. Experiments on the ISPRS, LoveDA, and OpenEarthMap benchmarks cover nine cross-domain transfers. ASCoR achieves a state-of-the-art mean IoU of 68.61% across six ISPRS transfers, outperforming the previous best method by 2.69 percentage points. It also achieves the best results on all three LoveDA/OpenEarthMap transfers, with 59.07%, 47.95%, and 49.38% mIoU on Rural-to-Urban, Urban-to-Rural, and Urban-to-OpenEarthMap, respectively. Ablation studies, feature visualizations, and spatial reliability analyses support the effectiveness and complementarity of the proposed components. Code: https://github.com/WangZitong42/ASCoR.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑