Abstract
Public remote sensing datasets often face limitations in universality due to resolution variability and inconsistent land cover category definitions. To harness the vast pool of unlabeled remote sensing data, we propose SAMST, a semi-supervised semantic segmentation method. SAMST leverages the strengths of the Segment Anything Model (SAM) in zero-shot generalization and boundary detection. SAMST iteratively refines pseudo-labels through two main components: supervised model self-training using both labeled and pseudo-labeled data, and a SAM-based Pseudo-label Refiner. The Pseudo-label Refiner comprises three modules: a Threshold Filter Module for preprocessing, a Prompt Generation Module for extracting connected regions and generating prompts for SAM, and a Label Refinement Module for final label stitching. By integrating the generalization power of large models with the training efficiency of small models, SAMST improves pseudo-label accuracy, thereby enhancing overall model performance. Experiments on the Potsdam dataset validate the effectiveness and feasibility of SAMST, demonstrating its potential to address the challenges posed by limited labeled data in remote sensing semantic segmentation.
Abstract (translated)
公共遥感数据集通常因分辨率变化和土地覆盖类别定义不一致而面临普遍性限制。为了利用大量未标注的遥感数据，我们提出了SAMST（一种半监督语义分割方法）。SAMST 利用了 Segment Anything 模型（SAM）在零样本泛化和边界检测方面的优势。SAMST 通过两个主要组成部分迭代地改进伪标签：一是使用标记和伪标记数据进行有监督模型自训练；二是基于 SAM 的伪标签细化器。该伪标签细化器包括三个模块：阈值过滤模块用于预处理，提示生成模块用于提取连接区域并为 SAM 生成提示，以及标签细化模块用于最终的标签拼接。通过结合大模型的泛化能力与小模型的训练效率，SAMST 提高了伪标签的准确性，从而提升了整体模型性能。在 Potsdam 数据集上的实验验证了 SAMST 的有效性和可行性，展示了其解决遥感语义分割中有限标记数据挑战的巨大潜力。
URL
https://arxiv.org/abs/2507.11994
