Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.01910 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912572637184000 |
|---|---|
| author | Jia, Furong Liu, Lanxin Hou, Ce Zhang, Fan Liu, Xinyan Liu, Yu |
| author_facet | Jia, Furong Liu, Lanxin Hou, Ce Zhang, Fan Liu, Xinyan Liu, Yu |
| contents | Worldwide geo-localization involves determining the exact geographic location of images captured globally, typically guided by geographic cues such as climate, landmarks, and architectural styles. Despite advancements in geo-localization models like GeoCLIP, which leverages images and location alignment via contrastive learning for accurate predictions, the interpretability of these models remains insufficiently explored. Current concept-based interpretability methods fail to align effectively with Geo-alignment image-location embedding objectives, resulting in suboptimal interpretability and performance. To address this gap, we propose a novel framework integrating global geo-localization with concept bottlenecks. Our method inserts a Concept-Aware Alignment Module that jointly projects image and location embeddings onto a shared bank of geographic concepts (e.g., tropical climate, mountain, cathedral) and minimizes a concept-level loss, enhancing alignment in a concept-specific subspace and enabling robust interpretability. To our knowledge, this is the first work to introduce interpretability into geo-localization. Extensive experiments demonstrate that our approach surpasses GeoCLIP in geo-localization accuracy and boosts performance across diverse geospatial prediction tasks, revealing richer semantic insights into geographic decision-making processes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_01910 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Interpretable Geo-localization: a Concept-Aware Global Image-GPS Alignment Framework Jia, Furong Liu, Lanxin Hou, Ce Zhang, Fan Liu, Xinyan Liu, Yu Computer Vision and Pattern Recognition Artificial Intelligence Worldwide geo-localization involves determining the exact geographic location of images captured globally, typically guided by geographic cues such as climate, landmarks, and architectural styles. Despite advancements in geo-localization models like GeoCLIP, which leverages images and location alignment via contrastive learning for accurate predictions, the interpretability of these models remains insufficiently explored. Current concept-based interpretability methods fail to align effectively with Geo-alignment image-location embedding objectives, resulting in suboptimal interpretability and performance. To address this gap, we propose a novel framework integrating global geo-localization with concept bottlenecks. Our method inserts a Concept-Aware Alignment Module that jointly projects image and location embeddings onto a shared bank of geographic concepts (e.g., tropical climate, mountain, cathedral) and minimizes a concept-level loss, enhancing alignment in a concept-specific subspace and enabling robust interpretability. To our knowledge, this is the first work to introduce interpretability into geo-localization. Extensive experiments demonstrate that our approach surpasses GeoCLIP in geo-localization accuracy and boosts performance across diverse geospatial prediction tasks, revealing richer semantic insights into geographic decision-making processes. |
| title | Towards Interpretable Geo-localization: a Concept-Aware Global Image-GPS Alignment Framework |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.01910 |