U-Net allows for seamless segmentation of 2D images, with high accuracy and performance.
UNet was first introduced by Olaf Ronneberger, Philip Fischer, and Thomas Brox in the paper: UNet: Convolutional Networks for Biomedical Image Segmentation. UNet allows for seamless segmentation of 2D images, with high accuracy and performance, and can be adapted to solve many different segmentation problems.
The following figure shows the construction of the UNet model and its different components. UNet is composed of a contractive and an expanding path, that aims at building a bottleneck in its centermost part through a combination of convolution and pooling operations. After this bottleneck, the image is reconstructed through a combination of convolutions and upsampling. Skip connections are added with the goal of helping the backward flow of gradients in order to improve the training.
Figure 1. UNet architecture
This model was trained using script available on NGC and in GitHub repo.
The following datasets were used to train this model:
Performance numbers for this model are available in NGC.