发表机构
heu（哈尔滨工程大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
跨视角地理定位中现有监督和无监督方法有局限，本文提出STEAM框架，通过稳定空间感知模块、弹性匹配和自适应净化进行自训练，在相关基准测试中性能达最优，验证了该框架在无监督跨视角地理定位中的有效性和优越性。
AI 中文摘要
跨视角地理定位（CVGL）旨在通过将无人机视角图像与相应卫星视角图像匹配来实现无GPS定位。现有监督方法依赖大规模人工标注的跨视角图像对，成本高且难以扩展。无监督方法易受分布偏差和噪声伪标签积累影响。本文提出STEAM，一个端到端无监督跨视角地理定位框架，直接在真实无人机和卫星图像上进行自训练。具体包括增强特征表示稳定性的模块、发现高质量伪标签的弹性匹配以及在自训练过程中动态维护可靠伪标签库的自适应净化。在相关基准测试上的实验表明，STEAM在无监督方法中达到最优性能，且与监督方法相当，验证了框架的有效性和优越性。
英文摘要
Cross-view geo-localization (CVGL) aims to achieve GPS-free localization by matching drone-view images with corresponding satellite-view images. Existing supervised methods rely on large-scale manually annotated cross-view image pairs, making them costly and difficult to scale. In contrast, existing unsupervised approaches typically depend on generative models or clustering-based stage-wise optimization, which are prone to distribution bias and the accumulation of noisy pseudo-labels. To address these limitations, we propose STEAM (Stable Self-Training with Elastic Matching and Adaptive Purification), an end-to-end unsupervised cross-view geo-localization framework that performs self-training directly on real drone and satellite images. Specifically, the proposed Stable Spatial-Aware Module enhances the stability of feature representations, Elastic Matching discovers high-quality cross-view pseudo-labels, and Adaptive Purification dynamically maintains a reliable pseudo-label repository throughout the self-training process. Extensive experiments on the University-1652 and SUES-200 benchmarks demonstrate that STEAM achieves state-of-the-art performance among all existing unsupervised methods and delivers performance comparable to supervised approaches, validating the effectiveness and superiority of the proposed framework. The source code is available at https://github.com/wsx-heu/STEAM.git.
