Learnable Query Aggregation with KV Routing for Cross-view Geo-localisation

TL;DR

This paper introduces a novel cross-view geo-localisation system that enhances feature aggregation and alignment through a DINOv2 backbone, multi-scale channel reallocation, and a Mixture-of-Experts routing mechanism, achieving competitive results.

Contribution

The paper presents a new CVGL approach with a learnable query aggregation method using MoE routing, improving adaptability and efficiency over previous methods.

Findings

Achieves competitive performance on University-1652 and SUES-200 datasets.

Uses fewer trained parameters than existing methods.

Demonstrates improved feature diversity and stability.

Abstract

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.