3CNet

This project provides the code and results for '3CNet: Cross-modal cooperative correction network for RGB-T semantic segmentation'.

Thank you for your interest. The complete training scripts and details will be made publicly available upon publication

Usage

Requirements

1. Python 3.8+
2. PyTorch 1.7.0+
3. CUDA 11.7+

and pip install -r requirements.txt

Note:For a detailed environment configuration tutorial you can refer to our CSDN blog.

Datasets

dataset

• mfnet/
  • RGB/
    • name1.png
    • name2.png
  • TH/
    • ……
  • Labels/
    • ……
• PST900/
  • ……

Pretrain weights:

Download the pretrained segformer(MiT-B2) here pretrained segformer.

Config

The parameters of the dataset and the network can be modified through this config file.

Results

Results on MFNet (9-class):

Backbone	Modal	mIoU
MiT-B2	RGB-T	60.0

The trained model can be downloaded here.

The visualisation of the model predictions can be downloaded here.

All code will be made public after the paper is published.