遥感图像开放词汇分割：基准与评测 Exploring Efficient Open-Vocabulary Segmentation in the Remote Sensing

精读摘要

开放词汇遥感图像分割（OVRSIS）把开放词汇分割引入遥感领域，但由于缺乏统一评测基准、自然图像与遥感图像之间存在域差距，这一方向研究不足。团队先基于广泛使用的遥感分割数据集建立标准化基准 OVRSISBench，实现方法间的可比评测，再用它系统评估多种代表性方法，为遥感图像理解的高效开放词汇分割铺路。 Open-Vocabulary Remote Sensing Image Segmentation remains underexplored due to the absence of a unified evaluation benchmark and the domain gap between natural and remote sensing images. The authors first establish OVRSISBench, a standardized benchmark based on widely-used RS segmentation datasets, then comprehensively evaluate representative methods. It lays groundwork for efficient open-vocabulary segmentation in remote sensing.