Speeding up Semantic Segmentation for Autonomous Driving

Michael Treml, José Arjona-Medina, Thomas Unterthiner, Rupesh Durgesh, Felix Friedmann, Peter Schuberth, Andreas Mayr, Martin Heusel, Markus Hofmarcher, Michael Widrich, Ulrich Bodenhofer, Bernhard Nessler, Sepp Hochreiter

NIPS 2016 Workshop - MLITS, 2016

Deep learning has considerably improved semantic image segmentation. However, its high accuracy is traded against larger computational costs which makes it unsuit- able for embedded devices in self-driving cars. We propose a novel deep network architecture for image segmentation that keeps the high accuracy while being efficient enough for embedded devices. The architecture consists of ELU activation functions, a SqueezeNet-like encoder, followed by parallel dilated convolutions, and a decoder with SharpMask-like refinement modules. On the Cityscapes dataset, the new network achieves higher segmentation accuracy than other networks that are tailored to embedded devices. Simultaneously the frame-rate is still sufficiently high for the deployment in autonomous vehicles.