ShuffleSeg: Real-time Semantic Segmentation Network release_yjt6brvxzjdvjcaj2rfyp4p554

by Mostafa Gamal, Mennatullah Siam, Moemen Abdel-Razek

Released as a article .



Real-time semantic segmentation is of significant importance for mobile and robotics related applications. We propose a computationally efficient segmentation network which we term as ShuffleSeg. The proposed architecture is based on grouped convolution and channel shuffling in its encoder for improving the performance. An ablation study of different decoding methods is compared including Skip architecture, UNet, and Dilation Frontend. Interesting insights on the speed and accuracy tradeoff is discussed. It is shown that skip architecture in the decoding method provides the best compromise for the goal of real-time performance, while it provides adequate accuracy by utilizing higher resolution feature maps for a more accurate segmentation. ShuffleSeg is evaluated on CityScapes and compared against the state of the art real-time segmentation networks. It achieves 2x GFLOPs reduction, while it provides on par mean intersection over union of 58.3% on CityScapes test set. ShuffleSeg runs at 15.7 frames per second on NVIDIA Jetson TX2, which makes it of great potential for real-time applications.
In text/plain format

Archived Files and Locations

application/pdf  778.6 kB
file_npfgfdk53je5lbf4e3dtgjtfea (webarchive) (repository)
Read Archived PDF
Type  article
Stage   submitted
Date   2018-03-10
Version   v1
Language   en ?
arXiv  1803.03816v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: cf333c20-908a-4fb3-86b8-ede0dfc46e3c