Model Overview

U-Net allows for seamless segmentation of 2D images, with high accuracy and performance.

Model Architecture

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

Training

This model was trained using script available on NGC and in GitHub repo.

Dataset

The following datasets were used to train this model:

• EM Segmentation - Set of 30 sections from a serial section Transmission Electron Microscopy (ssTEM) data set of the Drosophila first instar larva ventral nerve cord (VNC). The microcube measures 2 x 2 x 1.5 microns approx., with a resolution of 4x4x50 nm/pixel.

Performance

Performance numbers for this model are available in NGC.

References

• Original paper
• NVIDIA model implementation in NGC
• NVIDIA model implementation on GitHub

License

This model was trained using open-source software available in Deep Learning Examples repository. For terms of use, please refer to the license of the script and the datasets the model was derived from.