Learnable Query Aggregation with KV Routing for Cross-view Geo-localisation
This work addresses cross-view geo-localization for location estimation from images, presenting incremental improvements to existing methods.
The paper tackles cross-view geo-localization by addressing viewpoint discrepancies through three improvements: DINOv2 backbone fine-tuning, multi-scale channel reallocation, and a Mixture-of-Experts routing aggregation module. It achieves competitive performance on University-1652 and SUES-200 datasets with fewer trained parameters.
Cross-view geo-localisation (CVGL) aims to estimate the geographic location of a query image by matching it with images from a large-scale database. However, the significant view-point discrepancies present considerable challenges for effective feature aggregation and alignment. To address these challenges, we propose a novel CVGL system that incorporates three key improvements. Firstly, we leverage the DINOv2 backbone with a convolution adapter fine-tuning to enhance model adaptability to cross-view variations. Secondly, we propose a multi-scale channel reallocation module to strengthen the diversity and stability of spatial representations. Finally, we propose an improved aggregation module that integrates a Mixture-of-Experts (MoE) routing into the feature aggregation process. Specifically, the module dynamically selects expert subspaces for the keys and values in a cross-attention framework, enabling adaptive processing of heterogeneous input domains. Extensive experiments on the University-1652 and SUES-200 datasets demonstrate that our method achieves competitive performance with fewer trained parameters.