Skip to content

YininKorea/Contour-aware-equipotential-learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Equipotential Learning for Semantic Segmentation

This is an official implementation of Contour-Aware Equipotential Learning for Semantic Segmentation (accepted by IEEE TMM 2022) You can download all models in our paper at Google Drive

Overall Framework

overall framework

Acknowlegements

Our work (checkpoints) is an add-on approach and can be plugged into existing deep semantic segmentation models.

We achieved below PyTorch implementations to test our method:

  1. PSPNet & PSANet (including Pascal Voc and Cityscapes)
  2. (Pascal Voc only) DeepLab V3+
  3. (Cityscapes only) DeepLab V3+

The first repository is released by the author of PSPNet and PSANet, and we achieved powerful mIoU performances on both datasets with DeepLab V3+.

About

EPL (TMM'22)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages