Speeding up semantic segmentation for autonomous driving

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

Publikation: KonferenzbeitragPapierBegutachtung


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.
OriginalspracheEnglisch (Amerika)
PublikationsstatusVeröffentlicht - Dez. 2016
Extern publiziertJa
VeranstaltungNIPS Workshop on Machine Learning for Intelligent Transportation Systems - Barcelona, Spanien
Dauer: 8 Dez. 20168 Dez. 2016


WorkshopNIPS Workshop on Machine Learning for Intelligent Transportation Systems