An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions
Computer Vision and Pattern Recognition
2019-05-22 v2
Abstract
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.
Cite
@article{arxiv.1902.07476,
title = {An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions},
author = {Sercan Türkmen and Janne Heikkilä},
journal= {arXiv preprint arXiv:1902.07476},
year = {2019}
}
Comments
12 pages, 6 figures, 5 tables