发表机构
Tsinghua Shenzhen International Graduate School, Tsinghua University; School of Artificial Intelligence, Sun Yat-Sen University; Faculty of Geosciences and Engineering, Southwest Jiaotong University; College of Land Science and Technology, China Agricultural University; National Supercomputing Center in Shenzhen（清华大学深圳国际研究生院; 中山大学人工智能学院; 西南交通大学地球科学与环境工程学院; 中国农业大学土地科学与技术学院; 国家超级计算深圳中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对无源域跨场景高光谱图像分类问题，提出拓扑感知无源学习框架，通过EMP优化伪标签、CNT编码特征空间几何结构，实验表明其性能优于当前最优方法。
AI 中文摘要
域自适应技术推动了跨场景高光谱图像分类的发展，显著提升了复杂场景下的判别能力。但隐私法规或存储限制常导致无法获取源域数据，传统域自适应方法因此失效，严重制约其在实际遥感场景中的应用。为应对该挑战，本文提出拓扑感知无源学习框架：首先引入熵动量伪标签（EMP），通过利用熵感知置信度与时序预测动量优化k均值分配；在优化后伪标签的指导下，进一步利用上下文邻域拓扑（CNT）挖掘目标特征空间的内在几何结构，该方法结合协同表示提取的全局结构信息与近邻搜索建模的局部相似性信息，完成目标域特征空间流形级几何属性的全面编码；整体目标函数整合了优化后伪标签的交叉熵、基于对数内积的拓扑一致性项，以及用于平衡分类的信息最大化项，确保在无源域场景下实现稳定自适应。在三个典型跨场景上开展的大量实验表明，所提方法的性能优于当前最优方法， ablation研究进一步验证了各模块的贡献，结果凸显了拓扑感知建模在无源数据下实现鲁棒准确分类的关键作用。
英文摘要
Domain adaptation has advanced cross-scene hyperspectral image classification, significantly improving discriminative capability in complex scenarios. However, privacy rules or storage limits often block access to data from the source domain. Conventional domain adaptation methods become impractical, severely restricting their utility in realistic remote sensing scenarios. To tackle this challenge, we propose a topology-aware source-free learning framework. We first introduce the entropy momentum pseudo-labeling (EMP) to refine k-means assignments by leveraging entropy-aware confidence and temporal prediction momentum. Under the guidance of the refined pseudo-labels, we further utilize the contextual neighborhood topology (CNT) to exploit the intrinsic geometric structure of the target feature space. Combining the global structural information extracted by collaborative representation with the local similarity information modeled by nearest neighbor search, the CNT accomplishes the comprehensive encoding of manifold-level geometric properties in the target domain feature space. The overall objective integrates cross-entropy on refined pseudo-labels, log inner product-based topology consistency, and an information-maximization term for balanced classification, ensuring stable adaptation in the source-free setting. Extensive experiments on three typical cross-scenarios demonstrate that the proposed method exceeds state-of-the-art performance, and ablation studies further validate the contribution of each module. The results highlight the critical role of topology-aware modeling in achieving robust and accurate classification without source data.
