Research Article
Self-guided Few-Shot Semantic Segmentation for Remote Sensing Imagery Based on Large Vision Models
@INPROCEEDINGS{10.1007/978-3-031-71716-1_6, author={Xiyu Qi and Yifan Wu and Yongqiang Mao and Wenhui Zhang and Yidan Zhang}, title={Self-guided Few-Shot Semantic Segmentation for Remote Sensing Imagery Based on Large Vision Models}, proceedings={Machine Learning and Intelligent Communication. 8th EAI International Conference, MLICOM 2023, Beijing, China, December 17, 2023, Proceedings}, proceedings_a={MLICOM}, year={2024}, month={9}, keywords={Remote sensing images visual foundation model semantic segmentation prompt learning}, doi={10.1007/978-3-031-71716-1_6} }- Xiyu Qi
Yifan Wu
Yongqiang Mao
Wenhui Zhang
Yidan Zhang
Year: 2024
Self-guided Few-Shot Semantic Segmentation for Remote Sensing Imagery Based on Large Vision Models
MLICOM
Springer
DOI: 10.1007/978-3-031-71716-1_6
Abstract
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 mask to produce coarse pixel-wise prompts for SAM. Extensive experiments on the DLRSD datasets underlines the superiority of our approach, outperforming other available few-shot methodologies.
