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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bharadwaj, Siddhant, Vashist, Ashish, Aleem, Fahimul, Vyas, Shruti
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918452622524416
author Bharadwaj, Siddhant
Vashist, Ashish
Aleem, Fahimul
Vyas, Shruti
author_facet Bharadwaj, Siddhant
Vashist, Ashish
Aleem, Fahimul
Vyas, Shruti
contents 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 zero-shot reasoning capabilities across multimodal tasks, yet their performance in geographic inference remains underexplored. In this work, we present a systematic evaluation of multiple state-of-the-art VLMs for country-level image geolocalization using ground-view imagery only. Instead of relying on image matching, GPS metadata, or task-specific training, we evaluate prompt-based country prediction in a zero-shot setting. The selected models are tested on three geographically diverse datasets to assess their robustness and generalization ability. Our results reveal substantial variation across models, highlighting the potential of semantic reasoning for coarse geolocalization and the limitations of current VLMs in capturing fine-grained geographic cues. This study provides the first focused comparison of modern VLMs for country-level geolocalization and establishes a foundation for future research at the intersection of multimodal reasoning and geographic understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16248
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalization
Bharadwaj, Siddhant
Vashist, Ashish
Aleem, Fahimul
Vyas, Shruti
Computer Vision and Pattern Recognition
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 zero-shot reasoning capabilities across multimodal tasks, yet their performance in geographic inference remains underexplored. In this work, we present a systematic evaluation of multiple state-of-the-art VLMs for country-level image geolocalization using ground-view imagery only. Instead of relying on image matching, GPS metadata, or task-specific training, we evaluate prompt-based country prediction in a zero-shot setting. The selected models are tested on three geographically diverse datasets to assess their robustness and generalization ability. Our results reveal substantial variation across models, highlighting the potential of semantic reasoning for coarse geolocalization and the limitations of current VLMs in capturing fine-grained geographic cues. This study provides the first focused comparison of modern VLMs for country-level geolocalization and establishes a foundation for future research at the intersection of multimodal reasoning and geographic understanding.
title Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.16248