An Efficient Solution for Semantic Segmentation

Assigning a label to each pixel in an image, namely semantic segmentation, has been an important task in computer vision, and has applications in autonomous driving, robotic navigation, localization, and scene understanding. Fully convolutional neural networks have proved to be a successful solution for the task over the years but most of the work being done focuses primarily on accuracy. In this paper, we present a computationally efficient approach to semantic segmentation, while achieving a high mean intersection over union (mIOU), 70.33% on Cityscapes challenge. The network proposed is capable of running real-time on mobile devices. In addition, we make our code and model weights publicly available.

Türkmen Sercan, Heikkilä Janne

Publication type:
A4 Article in conference proceedings

Place of publication:
21st Scandinavian Conference, SCIA 2019, Norrköping, Sweden, June 11–13, 2019, Proceedings

Efficient; Fast, Lightweight, Mobile, Real-time, Semantic image segmentation


Full citation:
Türkmen S., Heikkilä J. (2019) An Efficient Solution for Semantic Segmentation: ShuffleNet V2 with Atrous Separable Convolutions. In: Felsberg M., Forssén PE., Sintorn IM., Unger J. (eds) Image Analysis. SCIA 2019. Lecture Notes in Computer Science, vol 11482. Springer, Cham


Read the publication here: