RSGPNet: Geometric Prompting for Remote Sensing Open-Vocabulary Semantic Segmentation
Open-vocabulary semantic segmentation (OVSS) enables text-guided segmentation of unseen objects, breaking fixed-class limitations to achieve open-world understanding. However, existing OVSS methods primarily focus on modifying the CLIP attention mechanism, which still suffers from unstable local segmentation for remote sensing (RS) domain. To address these limitations, we propose RSGPNet, a training-free geometric prompting framework for RS OVSS that refines segmentation by leveraging object geometric areas and consistency constraints. Specifically, RSGPNet comprises three core modules: a Text-guided Coarse Mask module (TCM), a Geometric Re-prompting Module (GRP), and a Coarse-to-fine Con...
| Authors | Shanwen Wang, Xin Sun, Sirui Wang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 25 June 2026 |
| Last updated at source | 25 June 2026 |
Connected in the knowledge graph
- fluorites/RSGPNetDataset · cited by
Models and datasets referencing this paper
- fluorites/RSGPNetDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.