kaggle上的常客(医学图像领域比较常用,也是car分割的冠军模型):
https://www.kaggle.com/c/data-science-bowl-2018/discussion/54426
U-Net: Convolutional Networks for Biomedical Image Segmentation
- VALID padding not SAME padding(因为边界用了镜像处理)
- matched lower and upper features after cropping lower feature(The cropping is necessary due to the loss of border pixels in every convolution:注意看图1中的虚线框,就是与右分支对应的位置去crop左分支)
- weighted cross entropy loss to separate instances
- elastic deformations
边界的镜像处理:
加权处理:类别平衡和给两个细胞之间的空隙更大的权重