【Dual Attentive Fully Convolutional Siamese Networks for Change Detection in High-Resolution Satellite Images】
论文:https://ieeexplore.ieee.org/document/9259045
【FULLY CONVOLUTIONAL SIAMESE NETWORKS FOR CHANGE DETECTION】
CSDN:https://blog.csdn.net/li_k_y/article/details/104930668
论文:https://arxiv.org/pdf/1810.08462.pdf
代码(torch):https://github.com/rcdaudt/fully_convolutional_change_detection
参考UNet结构,设计了三种结构
Unet结构如下
【Learning to Compare Image Patches via Convolutional Neural Networks】
论文:https://openaccess.thecvf.com/content_cvpr_2015/papers/Zagoruyko_Learning_to_Compare_2015_CVPR_paper.pdf
代码:https://github.com/szagoruyko/cvpr15deepcompare/tree/master/training
结论:2-channel结构最佳
【Learning to Measure Changes: Fully Convolutional Siamese Metric Networks for Scene Change Detection】
论文:https://arxiv.org/pdf/1810.09111.pdf
csdn:https://blog.csdn.net/li_k_y/article/details/104465170
代码(torch):https://github.com/gmayday1997/SceneChangeDet在这里插入图片描述
【SNUNet-CD: A Densely Connected Siamese Network for Change Detection of VHR Images】
论文:https://ieeexplore.ieee.org/document/9355573
代码(torch):https://github.com/likyoo/Siam-NestedUNet