RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation Based on Visual Foundation Model

Leveraging the extensive training data from SA-1B, the Segment Anything Model (SAM) demonstrates remarkable generalization and zero-shot capabilities. However, as a category-agnostic instance segmentation method, SAM heavily relies on prior manual guidance, including points, boxes, and coarse-grained masks. Furthermore, its performance in remote sensing image segmentation tasks remains largely unexplored and unproven. In this paper, we aim to develop an automated instance segmentation approach for remote sensing images, based on the foundational SAM model and incorporating semantic category information. Drawing inspiration from prompt learning, we propose a method to learn the generation of appropriate prompts…

• NN
  National Natural Science Foundation of China

  Award: 62125102
• NS
  Natural Science Foundation of Beijing Municipality

  Award: JL23005
• NK
  National Key Research and Development Program of China

  Award: 2022ZD0160401
• FR
  Fundamental Research Funds for the Central Universities