Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2506.01277 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910980167958528 |
|---|---|
| author | Yi, Qiang Shan, Lianlei |
| author_facet | Yi, Qiang Shan, Lianlei |
| contents | Accurately determining the geographic location where a single image was taken, visual geolocation, remains a formidable challenge due to the planet's vastness and the deceptive similarity among distant locations. We introduce GeoLocSFT, a framework that demonstrates how targeted supervised fine-tuning (SFT) of a large multimodal foundation model (Gemma 3) using a small, high-quality dataset can yield highly competitive geolocation performance. GeoLocSFT is trained with only 2700 carefully selected image-GPS pairs from our geographically diverse MR600k dataset. Despite this limited data, our SFT-centric approach substantially improves over baseline models and achieves robust results on standard benchmarks such as Im2GPS-3k and YFCC-4k, as well as on our newly proposed and challenging MR40k benchmark, aimed specifically at sparsely populated regions. Further, we explore multi-candidate inference and aggregation strategies but find that the core gains are already realized at the SFT stage. Our findings highlight the power of high-quality supervision and efficient SFT for planet-scale image geolocation, especially when compared to prior methods that require massive databases or complex pipelines. To foster further research, we publicly release the MR40k benchmark dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01277 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GeoLocSFT: Efficient Visual Geolocation via Supervised Fine-Tuning of Multimodal Foundation Models Yi, Qiang Shan, Lianlei Artificial Intelligence Accurately determining the geographic location where a single image was taken, visual geolocation, remains a formidable challenge due to the planet's vastness and the deceptive similarity among distant locations. We introduce GeoLocSFT, a framework that demonstrates how targeted supervised fine-tuning (SFT) of a large multimodal foundation model (Gemma 3) using a small, high-quality dataset can yield highly competitive geolocation performance. GeoLocSFT is trained with only 2700 carefully selected image-GPS pairs from our geographically diverse MR600k dataset. Despite this limited data, our SFT-centric approach substantially improves over baseline models and achieves robust results on standard benchmarks such as Im2GPS-3k and YFCC-4k, as well as on our newly proposed and challenging MR40k benchmark, aimed specifically at sparsely populated regions. Further, we explore multi-candidate inference and aggregation strategies but find that the core gains are already realized at the SFT stage. Our findings highlight the power of high-quality supervision and efficient SFT for planet-scale image geolocation, especially when compared to prior methods that require massive databases or complex pipelines. To foster further research, we publicly release the MR40k benchmark dataset. |
| title | GeoLocSFT: Efficient Visual Geolocation via Supervised Fine-Tuning of Multimodal Foundation Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2506.01277 |