JayQine / AMR

Apache License 2.0
63 stars 6 forks source link

Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation

This repository contains the pytorch codes and trained models described in the AAAI2022 paper "Activation Modulation and Recalibration Scheme for Weakly Supervised Semantic Segmentation".

Authors: Jie Qin, Jie Wu, Xuefeng Xiao, Lujun Li, Xingang Wang.

Overview

overview

Performance

performance

Prerequisites

Preparation

Dependencies

pip install -r requirements.txt

Dataset

Download PASCAL VOC 2012 follwing instructions in http://host.robots.ox.ac.uk/pascal/VOC/voc2012/#devkit.

Pretrained model

The pretrained model can be download in models.

Run

python run_sample.py --train_amr_pass True --make_cam_pass True --eval_cam_pass True

Eval

python run_sample.py --make_cam_pass True --eval_cam_pass True

Acknowledgement

We would like to thank the irn and the AdvCAM for their open-source projects.