Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.23938 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911344983277568 |
|---|---|
| author | Ye, Hualin Liu, Bingxi Du, Jixiang Qin, Yu Chen, Ziyi Zhang, Hong |
| author_facet | Ye, Hualin Liu, Bingxi Du, Jixiang Qin, Yu Chen, Ziyi Zhang, Hong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_23938 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learnable Query Aggregation with KV Routing for Cross-view Geo-localisation Ye, Hualin Liu, Bingxi Du, Jixiang Qin, Yu Chen, Ziyi Zhang, Hong Computer Vision and Pattern Recognition 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. |
| title | Learnable Query Aggregation with KV Routing for Cross-view Geo-localisation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.23938 |