WHU

该数据集是由武汉大学提供，用于训练建筑屋顶分割模型，旨在评估不同解释性人工智能（XAI）方法在语义分割任务中的性能。同时，该数据集也作为一个基准，以便比较不同XAI方法在卫星图像中分割建筑物的有效性。所涉及的任务是图像分割。

This dataset, provided by Wuhan University, is developed for training building roof segmentation models and aims to assess the performance of various eXplainable Artificial Intelligence (XAI) methods in semantic segmentation tasks. Additionally, this dataset serves as a benchmark for comparing the efficacy of different XAI methods for building segmentation in satellite imagery. The core task involved is image segmentation.