mmsegmentation/configs/cgnet
Junjun2016 36c81441c1
update metafiles (#661)
* update metafiles

* update metafiles
2021-07-01 22:31:00 +08:00
..
README.md comment tag (#505) 2021-04-24 09:58:59 -07:00
cgnet_512x1024_60k_cityscapes.py [New model] Support CGNet (#223) 2020-11-03 00:05:25 -08:00
cgnet_680x680_60k_cityscapes.py [New model] Support CGNet (#223) 2020-11-03 00:05:25 -08:00
metafile.yml update metafiles (#661) 2021-07-01 22:31:00 +08:00

README.md

CGNet: A Light-weight Context Guided Network for Semantic Segmentation

Introduction

@article{wu2020cgnet,
  title={Cgnet: A light-weight context guided network for semantic segmentation},
  author={Wu, Tianyi and Tang, Sheng and Zhang, Rui and Cao, Juan and Zhang, Yongdong},
  journal={IEEE Transactions on Image Processing},
  volume={30},
  pages={1169--1179},
  year={2020},
  publisher={IEEE}
}

Results and models

Cityscapes

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) config download
CGNet M3N21 680x680 60000 7.5 30.51 65.63 68.04 config model | log
CGNet M3N21 512x1024 60000 8.3 31.14 68.27 70.33 config model | log