NAVIG: Natural Language-guided Analysis with Vision Language Models for Image Geo-localization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913700757110784 |
|---|---|
| author | Zhang, Zheyuan Li, Runze Kabir, Tasnim Boyd-Graber, Jordan |
| author_facet | Zhang, Zheyuan Li, Runze Kabir, Tasnim Boyd-Graber, Jordan |
| contents | Image geo-localization is the task of predicting the specific location of an image and requires complex reasoning across visual, geographical, and cultural contexts. While prior Vision Language Models (VLMs) have the best accuracy at this task, there is a dearth of high-quality datasets and models for analytical reasoning. We first create NaviClues, a high-quality dataset derived from GeoGuessr, a popular geography game, to supply examples of expert reasoning from language. Using this dataset, we present Navig, a comprehensive image geo-localization framework integrating global and fine-grained image information. By reasoning with language, Navig reduces the average distance error by 14% compared to previous state-of-the-art models while requiring fewer than 1000 training samples. Our dataset and code are available at https://github.com/SparrowZheyuan18/Navig/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_14638 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NAVIG: Natural Language-guided Analysis with Vision Language Models for Image Geo-localization Zhang, Zheyuan Li, Runze Kabir, Tasnim Boyd-Graber, Jordan Computation and Language Computer Vision and Pattern Recognition Image geo-localization is the task of predicting the specific location of an image and requires complex reasoning across visual, geographical, and cultural contexts. While prior Vision Language Models (VLMs) have the best accuracy at this task, there is a dearth of high-quality datasets and models for analytical reasoning. We first create NaviClues, a high-quality dataset derived from GeoGuessr, a popular geography game, to supply examples of expert reasoning from language. Using this dataset, we present Navig, a comprehensive image geo-localization framework integrating global and fine-grained image information. By reasoning with language, Navig reduces the average distance error by 14% compared to previous state-of-the-art models while requiring fewer than 1000 training samples. Our dataset and code are available at https://github.com/SparrowZheyuan18/Navig/. |
| title | NAVIG: Natural Language-guided Analysis with Vision Language Models for Image Geo-localization |
| topic | Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.14638 |