.png){kind=icon}
.png){kind=icon}
Return
DGL-RSIS: Decoupling global spatial context and local class semantics for training-free remote sensing image segmentation
.png){kind=icon}
OA
AI
DOI：10.1016/j.jag.2026.105113.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• First training-free framework for universal remote sensing segmentation. • Decoupling local semantics and global context for both OVSS and RES tasks. • Enhancing local alignment via context-aware features and knowledge-guided prompts. • Global-enhanced Grad-CAM improves context reasoning and mask selection.
Keywords:
Vision language model
Open-vocabulary semantic segmentation
Referring expression segmentation
Domain knowledge
Training-free
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
8.6
Papers:
5.1K
Citations:
2.4W