Saved in:
Bibliographic Details
Main Authors: Li, Ling, Zhou, Yao, Liang, Yuxuan, Tsung, Fugee, Wei, Jiaheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.14674
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912667209302016
author Li, Ling
Zhou, Yao
Liang, Yuxuan
Tsung, Fugee
Wei, Jiaheng
author_facet Li, Ling
Zhou, Yao
Liang, Yuxuan
Tsung, Fugee
Wei, Jiaheng
contents Previous methods for image geo-localization have typically treated the task as either classification or retrieval, often relying on black-box decisions that lack interpretability. The rise of large vision-language models (LVLMs) has enabled a rethinking of geo-localization as a reasoning-driven task grounded in visual cues. However, two major challenges persist. On the data side, existing reasoning-focused datasets are primarily based on street-view imagery, offering limited scene diversity and constrained viewpoints. On the modeling side, current approaches predominantly rely on supervised fine-tuning, which yields only marginal improvements in reasoning capabilities. To address these challenges, we propose a novel pipeline that constructs a reasoning-oriented geo-localization dataset, MP16-Reason, using diverse social media images. We introduce GLOBE, Group-relative policy optimization for Localizability assessment and Optimized visual-cue reasoning, yielding Bi-objective geo-Enhancement for the VLM in recognition and reasoning. GLOBE incorporates task-specific rewards that jointly enhance localizability assessment, visual-cue reasoning, and geolocation accuracy. Both qualitative and quantitative results demonstrate that GLOBE outperforms state-of-the-art open-source LVLMs on geo-localization tasks, particularly in diverse visual scenes, while also generating more insightful and interpretable reasoning trajectories. The data and code are available at https://github.com/lingli1996/GLOBE.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14674
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
Li, Ling
Zhou, Yao
Liang, Yuxuan
Tsung, Fugee
Wei, Jiaheng
Computer Vision and Pattern Recognition
Previous methods for image geo-localization have typically treated the task as either classification or retrieval, often relying on black-box decisions that lack interpretability. The rise of large vision-language models (LVLMs) has enabled a rethinking of geo-localization as a reasoning-driven task grounded in visual cues. However, two major challenges persist. On the data side, existing reasoning-focused datasets are primarily based on street-view imagery, offering limited scene diversity and constrained viewpoints. On the modeling side, current approaches predominantly rely on supervised fine-tuning, which yields only marginal improvements in reasoning capabilities. To address these challenges, we propose a novel pipeline that constructs a reasoning-oriented geo-localization dataset, MP16-Reason, using diverse social media images. We introduce GLOBE, Group-relative policy optimization for Localizability assessment and Optimized visual-cue reasoning, yielding Bi-objective geo-Enhancement for the VLM in recognition and reasoning. GLOBE incorporates task-specific rewards that jointly enhance localizability assessment, visual-cue reasoning, and geolocation accuracy. Both qualitative and quantitative results demonstrate that GLOBE outperforms state-of-the-art open-source LVLMs on geo-localization tasks, particularly in diverse visual scenes, while also generating more insightful and interpretable reasoning trajectories. The data and code are available at https://github.com/lingli1996/GLOBE.
title Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.14674