The Segment Anything Model (SAM) exhibits remarkable versatility and zero-shot learning abilities, owing largely to its extensive training data (SA-1B). Recognizing SAM's dependency on manual guidance given its category-agnostic nature, we identified unexplored potential within few-shot semantic segmentation tasks for remote sensing imagery. This research introduces a structured framework designed for the automation of few-shot semantic segmentation. It utilizes the SAM model and facilitates a more efficient generation of semantically discernible segmentation outcomes. Central to our methodology is a novel automatic prompt learning approach, leveraging prior guided masks to produce coarse pixel-wise prompts for SAM. Extensive experiments on the DLRSD datasets underline the superiority of our approach, outperforming other available few-shot methodologies.
@article{arxiv.2311.13200,
title = {Self-guided Few-shot Semantic Segmentation for Remote Sensing Imagery Based on Large Vision Models},
author = {Xiyu Qi and Yifan Wu and Yongqiang Mao and Wenhui Zhang and Yidan Zhang},
journal= {arXiv preprint arXiv:2311.13200},
year = {2023}
}