Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Framework
Keywords: Visual Geo-Localization, Large Vision-Language Model, Collaboration Social Network
TL;DR: We propose a novel framework, smileGeo, to adaptively integrate multiple LVLMs through discussion for visual geo-localization tasks.
Abstract: Visual geo-localization demands in-depth knowledge and advanced reasoning skills to associate images with real-world geographic locations precisely.
In general, traditional methods based on data-matching are hindered by the impracticality of storing adequate visual records of global landmarks.
Recently, Large Vision-Language Models (LVLMs) have demonstrated the capability of geo-localization through Visual Question Answering (VQA), enabling a solution that does not require external geo-tagged image records. However, the performance of a single LVLM is still limited by its intrinsic knowledge and reasoning capabilities.
Along this line, in this paper, we introduce a novel visual geo-localization framework called smileGeo that integrates the inherent knowledge of multiple LVLM agents via inter-agent communication to achieve effective geo-localization of images.
Furthermore, our framework employs a dynamic learning strategy to optimize the communication patterns among agents, reducing unnecessary discussions among agents and improving the efficiency of the framework.
To validate the effectiveness of the proposed framework, we construct GeoGlobe, a novel dataset for visual geo-localization tasks. Extensive testing on the dataset demonstrates that our approach significantly outperforms state-of-the-art methods.
The source code is available at https://anonymous.4open.science/r/ViusalGeoLocalization-F8F5/ and the dataset will also be released after the paper is accepted.
Primary Area: Machine learning for other sciences and fields
Submission Number: 15517
Loading