Fig. 2From: Automated cephalometric landmark detection with confidence regions using Bayesian convolutional neural networksThe model architecture of our landmark detecting framework. The architecture has 4 Convolutional Cluster (CC) and 2 Fully Connected (FC) layers. Each CC contains the Batch Normalization layer, Convolution layer, Non-linearity, 2D max-pooling, and dropout in the mentioned orderBack to article page