论文地址：A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation
一篇对Tversky Loss进行改进的论文，网络的结构为Attention U-net
新增加了多尺度输入，多层次的预测结果作为loss
Focal Tversky Loss
Tversky similaryity index：
中间层使用FTL，最后层使用Tversky Loss
[深度学习从入门到女装]A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentatio
猜你喜欢
转载自blog.csdn.net/py184473894/article/details/100160728
今日推荐
周排行