GMNet

Code and result about GMNet(IEEE TIP)
'GMNet: Graded-Feature Multilabel-Learning Network for RGB-Thermal Urban Scene Semantic Segmentation' IEEE TIP

Requirements

Python 3.6.5, Pytorch 1.8.1+, Cuda 10.2, TensorboardX 2.0, opencv-python

Dataset and Evaluate tools

The MFNet datesets for RGB-T semantic segmentation could be found in 百度网盘 提取码：fgyx
(We also provide the label.)

Result

Predict maps: 百度网盘 提取码：v1fy
Pretrained model download:百度网盘 提取码：6hip

Citation

@ARTICLE{9531449,
author={Zhou, Wujie and Liu, Jinfu and Lei, Jingsheng and Yu, Lu and Hwang, Jenq-Neng},
journal={IEEE Transactions on Image Processing},
title={GMNet: Graded-Feature Multilabel-Learning Network for RGB-Thermal Urban Scene Semantic Segmentation},
year={2021},
volume={30},
number={},
pages={7790-7802},
doi={10.1109/TIP.2021.3109518}}

Acknowledgement

The implement of this project is based on the code of ‘RTFNet: RGB-Thermal Fusion Network for Semantic Segmentation of Urban Scenes (IEEE RAL)’ proposed by Yuxiang Sun et all.

Contact

Please drop me an email for further problems or discussion: tjuliujinfu@outlook.com or  wujiezhou@163.com (https://wujiezhou.github.io/)