GeoAlignCLIP: Enhancing Fine-Grained Vision-Language Alignment in Remote Sensing via Multi-Granular Consistency Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908876988743680 |
|---|---|
| author | Yang, Xiao Fu, Ronghao Duan, Zhuoran Lin, Zhiwen Liu, Xueyan Yang, Bo |
| author_facet | Yang, Xiao Fu, Ronghao Duan, Zhuoran Lin, Zhiwen Liu, Xueyan Yang, Bo |
| contents | Vision-language pretraining models have made significant progress in bridging remote sensing imagery with natural language. However, existing approaches often fail to effectively integrate multi-granular visual and textual information, relying primarily on global image-text alignment. This limitation hinders the model's ability to accurately capture fine-grained details in images, thus restricting its performance in complex, fine-grained tasks. To address this, we propose GeoAlignCLIP, a unified framework that achieves fine-grained alignment in remote sensing tasks by learning multi-granular semantic alignments and incorporating intra-modal consistency, enabling more precise visual-semantic alignment between image regions and text concepts. Additionally, we construct RSFG-100k, a fine-granular remote sensing dataset containing scene descriptions, region-level annotations, and challenging hard-negative samples, providing hierarchical supervision for model training. Extensive experiments conducted on multiple public remote-sensing benchmarks demonstrate that GeoAlignCLIP consistently outperforms existing RS-specific methods across diverse tasks, exhibiting more robust and accurate fine-grained vision-language alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09566 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GeoAlignCLIP: Enhancing Fine-Grained Vision-Language Alignment in Remote Sensing via Multi-Granular Consistency Learning Yang, Xiao Fu, Ronghao Duan, Zhuoran Lin, Zhiwen Liu, Xueyan Yang, Bo Computer Vision and Pattern Recognition Vision-language pretraining models have made significant progress in bridging remote sensing imagery with natural language. However, existing approaches often fail to effectively integrate multi-granular visual and textual information, relying primarily on global image-text alignment. This limitation hinders the model's ability to accurately capture fine-grained details in images, thus restricting its performance in complex, fine-grained tasks. To address this, we propose GeoAlignCLIP, a unified framework that achieves fine-grained alignment in remote sensing tasks by learning multi-granular semantic alignments and incorporating intra-modal consistency, enabling more precise visual-semantic alignment between image regions and text concepts. Additionally, we construct RSFG-100k, a fine-granular remote sensing dataset containing scene descriptions, region-level annotations, and challenging hard-negative samples, providing hierarchical supervision for model training. Extensive experiments conducted on multiple public remote-sensing benchmarks demonstrate that GeoAlignCLIP consistently outperforms existing RS-specific methods across diverse tasks, exhibiting more robust and accurate fine-grained vision-language alignment. |
| title | GeoAlignCLIP: Enhancing Fine-Grained Vision-Language Alignment in Remote Sensing via Multi-Granular Consistency Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.09566 |