Real-Time Semantic Segmentation with Label Propagation

Rasha Sheikh, Martin Garbade, Juergen Gall

Abstract: Despite of the success of convolutional neural networks for semantic image segmentation, CNNs cannot be used for many applications due to limited computational resources. Even efficient approaches based on random forests are not efficient enough for real-time performance in some cases. In this work, we propose an approach based on superpixels and label propagation that reduces the runtime of a random forest approach by factor 192 while increasing the segmentation accuracy.