Toshiba Cambridge Research Laboratory
Cambridge Research Laboratory > Computer Vision > CVG Resources > ContextNet Segmentation DNN

ContextNet Segmentation DNN

Drawing of a two-branch neural network for semantic segmentation.

If you compare or use our network in your work, please cite the following paper:

ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time
R. P. K. Poudel, U. Bonde, S. Liwicki and C. Zach
BMVC 2018  arXiv free

The network design and its training process is provided in the source files, and is to be used for research only. You will require Python, Tensorflow with GPU support and OpenCV2 to run the scripts. We use the Cityscapes dataset for training.

Download Tensorflow Model of ContextNet

To Top