Skip to content

README.md

Latest commit

 

History

History
74 lines (51 loc) · 2.63 KB

README.md

File metadata and controls

74 lines (51 loc) · 2.63 KB

📌 MiLNet

Multiplex Interactive Learning Network for RGB-T Semantic Segmentation (IEEE TIP)

🚀 Code and results for MiLNet (Published in IEEE TIP)

MiLNet Overview

🔧 Requirements

conda env create -f environment.yaml

📂 Toolbox

Please put the toolbox into the 📂 MiLNet-main.

📂 Dataset and Evaluation Tools

🔹 MFNet Dataset (for RGB-T semantic segmentation): Google Drive (Labels included)

🔹 PST900 Dataset (for RGB-T semantic segmentation): Google Drive

📥 Pretrained Models & Results

📌 Backbone Pretrained Model: Download

📌 MFNet:

📌 PST900:

📖 Citation

If you find this project helpful, please cite:

@ARTICLE{ljf2025milnet,
  author={Liu, Jinfu and Liu, Hong and Li, Xia and Ren, Jiale and Xu, Xinhua},
  journal={IEEE Transactions on Image Processing}, 
  title={MiLNet: Multiplex Interactive Learning Network for RGB-T Semantic Segmentation}, 
  year={2025},
  volume={34},
  number={},
  pages={1686-1699},
  keywords={},
  doi={10.1109/TIP.2025.3544484}}

✏️ You may refer to the following statement in your related work:

Liu et al. first proposed a multiplex interactive learning framework to facilitate mutual learning between cross-modal high- and low-level features, achieving complexity substitution by interaction instead of model parameters.

🎖 Acknowledgement

This project is implemented based on the code from MMSMCNet: Modal Memory Sharing and Morphological Complementary Networks for RGB-T Urban Scene Semantic Segmentation by Wujie Zhou, Han Zhang et al.

📬 Contact

📩 For any inquiries or discussions, feel free to contact me at: liujinfu@stu.pku.edu.cn