Skip to content
No description, website, or topics provided.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

C3 and SINet for Lightweight segmentaiton model on Cityscape dataset

Our code will be released in this link after security check. I guess next week. However if you have questions, please mail to me. I am happy to wait for your question mail.


  • python 3.6
  • pytorch >= 0.4.1
  • torchvision==0.2.1
  • opencv-python==
  • numpy
  • tensorboardX
  • visdom


Hyojin Park, Youngjoon Yoo, Geonseok Seo, Dongyoon Han, Sangdoo Yun, Nojun Kwak " C3: Concentrated-Comprehensive Convolution and its application to semantic segmentation " (paper)

Hyojin Park, Lars Lowe Sjösund, YoungJoon Yoo, Nicolas Monet, Nojun Kwak " SINet: Extreme Lightweight Portrait Segmentation Networks with Spatial Squeeze Modules and Information Blocking Decoder" (paper)

Model # of Param(M) # of Flop(G) size for Flop IoU( val ) IoU (test) server link
C3Net[2,3,7,13] 0.19 3.15 512*1024 66.87 64.78 link
C3NetV2[2,4,8,16] 0.18 2.66 512*1024 66.28 65.48 link
SINet 0.12 1.22 1024*2048 68.22 66.46 link
  • C3NetV2 has same encoder structure with C3Net, but uses bilinear upsampling for a decodder structure.


Once you train the model, my code automatically export format for Cityscape Testserver from best training model. I used P-40 GPU for training. C3 and C3_V2 require 2 GPU and SINet needs 1 GPU.

python -c C3.json

python -c C3_V2.json

python -c SINet.json


We are grateful to Clova AI, NAVER with valuable discussions.

I also appreciate my co-authors YoungJoon Yoo, Dongyoon Han, Sangdoo Yun and Lars Lowe Sjösund from Clova AI, NAVER, and Nicolas Monet from NAVER LABS Europe.

I refer ESPNet code for constructing my experiments and also appreciate Sachin Mehta for valuable comments. Sachin Mehta is ESPNet and ESPNetV2 author.

You can’t perform that action at this time.