Geospatial-Reasoning-Driven Vocabulary-Agnostic Remote Sensing Semantic Segmentation
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_ | 1866917507229548544 |
|---|---|
| author | Zhou, Chufeng Wang, Jian Liu, Xinyuan Zhang, Xiaokang |
| author_facet | Zhou, Chufeng Wang, Jian Liu, Xinyuan Zhang, Xiaokang |
| contents | Open-vocabulary semantic segmentation has become an important direction in remote sensing, as it enables recognition beyond predefined land-cover categories. However, existing methods mainly depend on passive visual-text matching and often struggle with semantic ambiguity in geographically complex scenes, especially when different classes exhibit similar spectral or structural patterns. To address this issue, we propose a Geospatial Reasoning Chain-of-Thought (GR-CoT) framework for remote sensing open-vocabulary semantic segmentation. GR-CoT consists of an offline knowledge distillation stream and an online instance reasoning stream. The former constructs category interpretation standards for confusing classes, while the latter performs macro-scenario anchoring, visual feature decoupling, and knowledge-driven decision synthesis to generate an image-adaptive vocabulary for downstream segmentation. Experiments on the LoveDA and GID5 benchmarks indicate that the proposed framework improves overall segmentation performance and yields more semantically coherent predictions in complex scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_08206 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Geospatial-Reasoning-Driven Vocabulary-Agnostic Remote Sensing Semantic Segmentation Zhou, Chufeng Wang, Jian Liu, Xinyuan Zhang, Xiaokang Computer Vision and Pattern Recognition Open-vocabulary semantic segmentation has become an important direction in remote sensing, as it enables recognition beyond predefined land-cover categories. However, existing methods mainly depend on passive visual-text matching and often struggle with semantic ambiguity in geographically complex scenes, especially when different classes exhibit similar spectral or structural patterns. To address this issue, we propose a Geospatial Reasoning Chain-of-Thought (GR-CoT) framework for remote sensing open-vocabulary semantic segmentation. GR-CoT consists of an offline knowledge distillation stream and an online instance reasoning stream. The former constructs category interpretation standards for confusing classes, while the latter performs macro-scenario anchoring, visual feature decoupling, and knowledge-driven decision synthesis to generate an image-adaptive vocabulary for downstream segmentation. Experiments on the LoveDA and GID5 benchmarks indicate that the proposed framework improves overall segmentation performance and yields more semantically coherent predictions in complex scenes. |
| title | Geospatial-Reasoning-Driven Vocabulary-Agnostic Remote Sensing Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.08206 |