Skip to content
/ OC-CSE Public
forked from KAIST-vilab/OC-CSE

Unlocking the Potential of Ordinary Classifier: Class-specific Adversarial Erasing Framework for Weakly Supervised Semantic Segmentation, ICCV 2021

License

Notifications You must be signed in to change notification settings

yoon307/OC-CSE

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

Unlocking the Potential of Ordinary Classifier: Class-specific Adversarial Erasing Framework for Weakly Supervised Semantic Segmentation

This repository contains the code (in PyTorch) for "Unlocking the Potential of Ordinary Classifier: Class-specific Adversarial Erasing Framework for Weakly Supervised Semantic Segmentation" paper (ICCV 2021) by Hyeokjun Kweon and Sung-Hoon Yoon.

Introduction

We have developed a framework that extract the potential of the ordinary classifier with class-specific adversarial erasing framework for weakly supervised semantic segmentation. With image-level supervision only, we achieved new state-of-the-arts both on PASCAL VOC 2012 and MS-COCO.

Citation

TBD

Prerequisite

TBD

Usage

TBD

TBD

Results and Trained Models

TBD

About

Unlocking the Potential of Ordinary Classifier: Class-specific Adversarial Erasing Framework for Weakly Supervised Semantic Segmentation, ICCV 2021

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published