Semantic segmentation is one of the fundamental tasks of pixel-level remote sensing image analysis. Currently, most high-performance semantic segmentation methods are trained in a supervised learning manner. These methods require a large number of image labels as support, but manual annotations are difficult to obtain. To address the problem, we propose an efficient unsupervised remote sensing image segmentation method based on superpixel segmentation and fully convolutional networks (FCNs) in this letter. Our method can achieve pixel-level images segmentation of various scales rapidly without any manual labels or prior knowledge. We use the superpixel segmentation results as synthetic ground truth to guide the gradient descent direction during FCN training. In experiments, our method achieved high performance compared with current unsupervised image segmentation methods on three public datasets. Specifically, our method achieves an adjusted mutual information (AMI) score of 0.2955 on the Gaofen Image Dataset (GID), while processing each image of size 7200 $\times6800$ pixels in just 30 s.

中文翻译：

---

一种超像素引导的无监督遥感图像快速语义分割方法

语义分割是像素级遥感影像分析的基本任务之一。目前，大多数高性能语义分割方法都是以监督学习的方式进行训练的。这些方法需要大量的图像标签作为支持，但人工标注很难获得。为了解决这个问题，我们在这封信中提出了一种基于超像素分割和全卷积网络（FCN）的高效无监督遥感图像分割方法。我们的方法可以在没有任何手动标签或先验知识的情况下快速实现各种尺度的像素级图像分割。我们使用超像素分割结果作为合成地面实况来指导 FCN 训练期间的梯度下降方向。在实验中，与当前在三个公共数据集上的无监督图像分割方法相比，我们的方法实现了高性能。具体来说，我们的方法在高分图像数据集 (GID) 上实现了 0.2955 的调整互信息 (AMI) 分数，同时处理大小为 7200 的每个图像 $\times6800$30 秒内的像素。