Drone-view geo-localization (DVGL) aims to achieve accurate localization of drones by retrieving the most relevant GNSS-tagged satellite images. However, most existing methods heavily rely on strictly prepaired drone-satellite images for supervised learning. When the target region shifts, new paired samples are typically required to adapt to the distribution changes. The high cost of annotation and the limited transferability of these methods significantly hinder the practical deployment of DVGL in open-world scenarios. To address these limitations, we propose a novel end-to-end self-supervised learning method with a shallow backbone network, called the dynamic memory-driven and neighborhood information learning (DMNIL) method. It employs a clustering algorithm to generate pseudolabels and adopts a dual-path contrastive learning framework to learn discriminative intraview representations. Furthermore, DMNIL incorporates two core modules, including the dynamic hierarchical memory learning (DHML) module andtheinformation consistency evolution learning (ICEL) module. The DHML module combines short-term and long-term memory to enhance intraview feature consistency and discriminability. Meanwhile, the ICEL module utilizes a neighborhood-driven collaborative constraint mechanism to systematically capture implicit crossview semantic correlations, consequently improving crossview feature alignment. To further stabilize and strengthen the self-supervised training process, a pseudolabel enhancement (PLE) strategy is introduced to enhance the quality of pseudo supervision. Extensive experiments on three public benchmark datasets demonstrate that the proposed method consistently outperforms existing self-supervised methods and even surpasses several state-of-the-art supervised methods. Our code is available at https://github.com/ISChenawei/DMNIL.
Chen et al. (Thu,) studied this question.