Query-Driven Feature Learning for Cross-View Geo-Localization

The cross-view geo-localization (CVGL) task aims to accurately retrieve a location using images captured from different platforms, such as satellites and drones, which is particularly challenging due to a large variation in viewpoint. Current methods mainly focus on rigid strategies such as partitioning or sorting local features, which may be ill-suited to accommodate the variance of viewpoint and distance scale in different camera perspectives. To address these issues, we propose a novel method called query-driven feature learning (QDFL) to query viewpoint-invariant feature vectors autonomously. Our method incorporates an adaptive query embedding unit (AQEU) and a feature fusion unit (FFU). AQEU adjusts feature map and implements a coarse query process to extract the contextual clues. FFU further refines feature map, fusing it at spatial and channel dimensions, tending to withdraw more fine-grained features. Subsequently, AQEU executes a fine query on salient landmarks in the fused feature map, enhancing the minutia descriptive power of query vectors. In addition, we use parameter-efficient transfer learning (PETL) manner by integrating tunable adapters into the frozen pretrained backbone, maintaining feature representation capabilities of foundation models while enabling seamless adaptation to CVGL task. Extensive experiments show that our method achieves state-of-the-art (SOTA) performances on two well-known datasets, University-1652 and SUES-200. Moreover, our method exhibits an excellent generalizability compared with current SOTA methods in cross-dataset experiments. The code is available at https://github.com/Shuyu-Hu/QDFL