Skip to content

Latest commit

 

History

History

icnet

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

ICNet

ICNet for Real-time Semantic Segmentation on High-resolution Images

Introduction

Official Repo

Code Snippet

Abstract

We focus on the challenging task of real-time 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 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 unit to quickly achieve high-quality segmentation. Our system yields real-time inference on a single GPU card with decent quality results evaluated on challenging datasets like Cityscapes, CamVid and COCO-Stuff.

Results and models

Cityscapes

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) Device mIoU mIoU(ms+flip) config download
ICNet R-18-D8 832x832 80000 1.70 27.12 V100 68.14 70.16 config model | log
ICNet R-18-D8 832x832 160000 - - V100 71.64 74.18 config model | log
ICNet (in1k-pre) R-18-D8 832x832 80000 - - V100 72.51 74.78 config model | log
ICNet (in1k-pre) R-18-D8 832x832 160000 - - V100 74.43 76.72 config model | log
ICNet R-50-D8 832x832 80000 2.53 20.08 V100 68.91 69.72 config model | log
ICNet R-50-D8 832x832 160000 - - V100 73.82 75.67 config model | log
ICNet (in1k-pre) R-50-D8 832x832 80000 - - V100 74.58 76.41 config model | log
ICNet (in1k-pre) R-50-D8 832x832 160000 - - V100 76.29 78.09 config model | log
ICNet R-101-D8 832x832 80000 3.08 16.95 V100 70.28 71.95 config model | log
ICNet R-101-D8 832x832 160000 - - V100 73.80 76.10 config model | log
ICNet (in1k-pre) R-101-D8 832x832 80000 - - V100 75.57 77.86 config model | log
ICNet (in1k-pre) R-101-D8 832x832 160000 - - V100 76.15 77.98 config model | log

Note: in1k-pre means pretrained model is used.

Citation

@inproceedings{zhao2018icnet,
  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},
  booktitle={Proceedings of the European conference on computer vision (ECCV)},
  pages={405--420},
  year={2018}
}