HRNET官方的语义分割部分 https://blog.csdn.net/weixin_37993251/article/details/88043650 https://jingdongwang2017.github.io/Projects/HRNet/index.html
商汤科技首届AI遥感解译大赛-变化检测赛道 (SenseTime, Aug 2020) 数据集:4662组,分辨率:0.5~3m,规格:512*512,变化类型为6种主要土地性质之间的相互转化:水体、地面、低矮植被、树木、建筑物、运动场。每组数据中,前后时相的两张图片各自对应一:https://github.com/LiheYoung/SenseEarth2020-ChangeDetection
这个是https://github.com/likyoo/Siam-NestedUNet这个,参考的一个项目
Fully convolutional siamese networks for change detection代码只有部分,在这篇博客(https://blog.csdn.net/li_k_y/article/details/104930668)下面,有一个类似的https://github.com/likyoo/Siam-NestedUNet
遥感图CD问题 https://paperswithcode.com/paper/dasnet-dual-attentive-fully-convolutional
https://paperswithcode.com/paper/learning-to-measure-change-fully https://arxiv.org/pdf/1810.09111v3.pdf
Fully Convolutional Siamese Networks for Change Detection https://paperswithcode.com/paper/fully-convolutional-siamese-networks-for https://arxiv.org/pdf/1810.08462v1.pdf