Multi-Level Correlation Network For Few-Shot Image Classification
(ICME 2023)

[paper]

✔️ Requirements

• Ubuntu 16.04
• Python 3.7
• CUDA 11.0
• PyTorch 1.7.1

⚙️ Conda environmnet installation

conda env create --name mlcn --file environment.yml
conda activate mlcn

📚 Datasets

cd datasets
bash download_miniimagenet.sh
bash download_cub.sh
bash download_cifar_fs.sh
bash download_tieredimagenet.sh

🔍 Related repos

Our project references the codes in the following repos:

• Zhang et al., DeepEMD.
• Ye et al., FEAT
• Kang et al., renet

💌 Acknowledgement

This paper adopted the main code bases from renet.

I also sincerely thank Min Zhang.

📜 Citing MLCN

If you find our code or paper useful to your research work, please consider citing our work using the following bibtex:

@inproceedings{dang2023multi,
  title={Multi-Level Correlation Network For Few-Shot Image Classification},
  author={Dang, Yunkai and Sun, Meijun and Zhang, Min and Chen, Zhengyu and Zhang, Xinliang and Wang, Zheng and Wang, Donglin},
  booktitle={2023 IEEE International Conference on Multimedia and Expo (ICME)},
  pages={2909--2914},
  year={2023},
  organization={IEEE}
}