MLRSNet 语义场景分类数据集

MLRSNet 是一个大规模的高分辨率多标签遥感数据集，用于语义场景理解。该数据集包含 109,161 张高分辨率遥感图像，这些图像被标注为 46 个类别，并且每个类别中的样本图像数量从 1,500 到 3,000 不等。图像的固定大小为 256×256 像素，具有各种像素分辨率。

MLRSNet is a large-scale high-resolution multi-label remote sensing dataset designed for semantic scene understanding. This dataset contains 109,161 high-resolution remote sensing images, which are annotated with 46 categories, and the number of sample images per category ranges from 1,500 to 3,000. All images have a fixed size of 256×256 pixels and feature various pixel resolutions.

搜集汇总

背景与挑战

背景概述

MLRSNet是一个大规模高分辨率多标签遥感数据集，包含109,161张256×256像素的图像，标注了46个类别，每个图像带有1-13个标签。该数据集适用于语义场景理解任务，如多标签图像分类、检索和分割。