Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.05501 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915625184526336 |
|---|---|
| author | Yuan, Yunshuang Thiemann, Frank Dahms, Thorsten Sester, Monika |
| author_facet | Yuan, Yunshuang Thiemann, Frank Dahms, Thorsten Sester, Monika |
| contents | Historical maps offer valuable insights into changes on Earth's surface but pose challenges for modern segmentation models due to inconsistent visual styles and symbols. While deep learning models such as UNet and pre-trained foundation models perform well in domains like autonomous driving and medical imaging, they struggle with the variability of historical maps, where similar concepts appear in diverse forms. To address this issue, we propose On-Need Declarative (OND) knowledge-based prompting, a method that provides explicit image-label pair prompts to guide models in linking visual patterns with semantic concepts. This enables users to define and segment target concepts on demand, supporting flexible, concept-aware segmentation. Our approach replaces the prompt encoder of the Segment Anything Model (SAM) with the OND prompting mechanism and fine-tunes it on historical maps, creating SMOL-MapSeg (Show Me One Label). Unlike existing SAM-based fine-tuning methods that are class-agnostic or restricted to fixed classes, SMOL-MapSeg supports class-aware segmentation across arbitrary datasets. Experiments show that SMOL-MapSeg accurately segments user-defined classes and substantially outperforms baseline models. Furthermore, it demonstrates strong generalization even with minimal training data, highlighting its potential for scalable and adaptable historical map analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05501 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SMOL-MapSeg: Show Me One Label as prompt Yuan, Yunshuang Thiemann, Frank Dahms, Thorsten Sester, Monika Computer Vision and Pattern Recognition Historical maps offer valuable insights into changes on Earth's surface but pose challenges for modern segmentation models due to inconsistent visual styles and symbols. While deep learning models such as UNet and pre-trained foundation models perform well in domains like autonomous driving and medical imaging, they struggle with the variability of historical maps, where similar concepts appear in diverse forms. To address this issue, we propose On-Need Declarative (OND) knowledge-based prompting, a method that provides explicit image-label pair prompts to guide models in linking visual patterns with semantic concepts. This enables users to define and segment target concepts on demand, supporting flexible, concept-aware segmentation. Our approach replaces the prompt encoder of the Segment Anything Model (SAM) with the OND prompting mechanism and fine-tunes it on historical maps, creating SMOL-MapSeg (Show Me One Label). Unlike existing SAM-based fine-tuning methods that are class-agnostic or restricted to fixed classes, SMOL-MapSeg supports class-aware segmentation across arbitrary datasets. Experiments show that SMOL-MapSeg accurately segments user-defined classes and substantially outperforms baseline models. Furthermore, it demonstrates strong generalization even with minimal training data, highlighting its potential for scalable and adaptable historical map analysis. |
| title | SMOL-MapSeg: Show Me One Label as prompt |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.05501 |