17206

ICNet for Real-Time Semantic Segmentation on High-Resolution Images

Hengshuang Zhao, Xiaojuan Qi, Xiaoyong Shen, Jianping Shi, Jiaya Jia
The Chinese University of Hong Kong
arXiv:1704.08545 [cs.CV], (27 Apr 2017)

@article{zhao2017icnet,

   title={ICNet for Real-Time Semantic Segmentation on High-Resolution Images},

   author={Zhao, Hengshuang and Qi, Xiaojuan and Shen, Xiaoyong and Shi, Jianping and Jia, Jiaya},

   year={2017},

   month={apr},

   archivePrefix={"arXiv"},

   primaryClass={cs.CV}

}

Download Download (PDF)   View View   Source Source   

302

views

We focus on the challenging task of realtime semantic segmentation in this paper. It finds many practical applications and yet is with fundamental difficulty of reducing a large portion of computation for pixel-wise label inference. We propose an compressed-PSPNet-based image cascade network (ICNet) that incorporates multi-resolution branches under proper label guidance to address this challenge. We provide in-depth analysis of our framework and introduce the cascade feature fusion to quickly achieve high-quality segmentation. Our system yields realtime inference on a single GPU card with decent quality results evaluated on challenging Cityscapes dataset.
VN:F [1.9.22_1171]
Rating: 0.0/5 (0 votes cast)

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: