VimGeo: An Efficient Visual Model for Cross-View Geo-Localization

Yang Kaiqian; Yujin Zhang; Li Wang; Muzahid A. A. M.; Sohel Ferdous; Fei Wu; Qiong Wu

doi:10.3390/electronics14193906

Back

VimGeo: An Efficient Visual Model for Cross-View Geo-Localization

Journal article

Open access

Peer reviewed

VimGeo: An Efficient Visual Model for Cross-View Geo-Localization

Yang Kaiqian, Yujin Zhang, Li Wang, Muzahid A. A. M., Sohel Ferdous, Fei Wu and Qiong Wu

Electronics (Basel), Vol.14(19), 3906

2025

DOI: https://doi.org/10.3390/electronics14193906

Files and links (1)

pdf

Published4.39 MBDownload View

CC BY V4.0, Open Access

Abstract

Algorithms

Computer vision

Datasets

Deep learning

Efficiency

Localization

Neural networks

Remote sensing

Semantics

State space models

Vision

Cross-view geo-localization is a challenging task due to the significant changes in the appearance of target scenes from variable perspectives. Most existing methods primarily adopt Transformers or ConvNeXt as backbone models but often face high computational costs and accuracy degradation in complex scenarios. Therefore, this paper proposes a visual Mamba framework based on the state-space model (SSM) for cross-view geo-localization. Compared with the existing methods, Vision Mamba is more efficient in modeling and memory usage and achieves more efficient cross-view matching by combining the twin architecture of shared weights with multiple mixed losses. Additionally, this paper introduces Dice Loss to handle scale differences and imbalance issues in cross-view images. Extensive experiments on the public cross-view dataset University-1652 demonstrate that Vision Mamba not only achieves excellent performance in UAV target localization tasks but also attains the highest efficiency with lower memory consumption. This work provides a novel solution for cross-view geo-localization tasks and shows great potential to become the backbone model for the next generation of cross-view geo-localization.

Details

Title: VimGeo: An Efficient Visual Model for Cross-View Geo-Localization
Authors/Creators: Yang Kaiqian
Yujin Zhang - Shanghai University of Engineering Science
Li Wang
Muzahid A. A. M.
Sohel Ferdous
Fei Wu - Shanghai University of Engineering Science
Qiong Wu - Shanghai University of Engineering Science
Publication Details: Electronics (Basel), Vol.14(19), 3906
Publisher: MDPI AG
Number of pages: 17
Identifiers: 991005821346007891
Murdoch Affiliation: School of Information Technology
Language: English
Resource Type: Journal article

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Source: InCites

Metrics

1 File views/ downloads

9 Record Views

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Citation topics: 4 Electrical Engineering, Electronics & Computer Science; 4.116 Robotics; 4.116.133 Simultaneous Localization and Mapping
Web Of Science research areas: Computer Science, Information Systems; Engineering, Electrical & Electronic; Physics, Applied
ESI research areas: Engineering