Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models

2025-06-17 · Ling Li, Yao Zhou, Yuxuan Liang, Fugee Tsung, Jiaheng Wei

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 Locatability assessment and Optimized visual-clue reasoning, yielding Bi-objective geo-Enhancement for the VLM in recognition and reasoning. GLOBE incorporates task-specific rewards that jointly enhance locatability assessment, visual clue 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.

📄 PDF Abstract BibTeX arXiv:2506.14674

Code (0)

등록된 구현이 없습니다.

Tasks

geo-localization

AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection

2026-02-09 · Junru Zhang, Lang Feng, Haoran Shi, Xu Guo 외 arxiv

Time-series anomaly detection (TSAD) with multimodal large language models (MLLMs) is an emerging area, yet a persistent challenge remains: MLLMs rely on coarse time-series heuristics but struggle with multi-dimensional,…

Anomaly Classification Reinforcement Learning Anomaly Detection

Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalization

2026-04-17 · Siddhant Bharadwaj, Ashish Vashist, Fahimul Aleem, Shruti Vyas arxiv

Image geolocalization has traditionally been addressed through retrieval-based place recognition or geometry-based visual localization pipelines. Recent advances in Vision-Language Models (VLMs) have demonstrated strong …

Multimodal Reasoning Visual Localization Image Matching

Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention

2026-05-21 · Changyuan Tian, Zhicong Lu, Huaxing Liu, Xiang Wang 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for advancing complex reasoning in large language models, and recent work extends RLVR to multimodal large language models (MLLMs)…

Reinforcement Learning Multimodal Reasoning

Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning

2026-02-16 · Jing Tang, Kun Wang, Haolang Lu, Hongjin Chen 외 arxiv

Multimodal large language models (MLLMs) in long chain-of-thought reasoning often fail when different knowledge sources provide conflicting signals. We formalize these failures under a unified notion of knowledge conflic…

Multimodal Reasoning

Reinforcing Generated Images via Meta-learning for One-Shot Fine-Grained Visual Recognition

2022-04-22 · Satoshi Tsutsui, Yanwei Fu, David Crandall

One-shot fine-grained visual recognition often suffers from the problem of having few training examples for new fine-grained classes. To alleviate this problem, off-the-shelf image generation techniques based on Generati…

Diversity Fine-Grained Image Classification Fine-Grained Visual Recognition image-classification+4