Skip to content

shijiangming1/MMM

Repository files navigation

MMM: Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification

Jiangming Shi · Xiangbo Yin · Yeyun Chen · Yachao Zhang · Zhizhong Zhang · Yuan Xie* · Yanyun Qu*

Access the research paper here

MMM This is an official code implementation of "MMM: Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification".

Requirements

# Install the required packages
pip install torch==1.8.0 torchvision==0.9.1+cu111 faiss-gpu==1.6.3 scikit-learn==1.3.2

Train/Test Instructions

# Training Steps

# Step 1: Obtain Features and Pseudo-Labels from Baseline Model
CUDA_VISIBLE_DEVICES=0,1 python Baseline.py --dataset sysu --data-dir sysu_dataset_path --iters 200 # for SYSU-MM01
CUDA_VISIBLE_DEVICES=0,1 python Baseline.py --dataset regdb --data-dir regdb_dataset_path --iters 100 # for REGDB



# Step 2: Train the MMM Model
CUDA_VISIBLE_DEVICES=0 python main.py --dataset sysu --data-dir sysu_dataset_path # for SYSU-MM01
CUDA_VISIBLE_DEVICES=0 python main.py --dataset regdb --data-dir regdb_dataset_path # for RegDB

# Testing 
CUDA_VISIBLE_DEVICES=0 python test.py --dataset sysu --data-dir sysu_dataset_path --resume-net1 modelname # for SYSU-MM01
CUDA_VISIBLE_DEVICES=3 python test.py --dataset regdb --data-dir regdb_dataset_path  --resume-net1 modelname # for RegDB

Citation

If our work is helpful for your research, please consider citing:

@article{shi2024multi,
  title={Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification},
  author={Shi, Jiangming and Yin, Xiangbo and Chen, Yeyun and Zhang, Yachao and Zhang, Zhizhong and Xie, Yuan and Qu, Yanyun},
  journal={arXiv preprint arXiv:2401.06825},
  year={2024}
}


@inproceedings{shi2023dpis,
  title={Dual pseudo-labels interactive self-training for semi-supervised visible-infrared person re-identification},
  author={Shi, Jiangming and Zhang, Yachao and Yin, Xiangbo and Xie, Yuan and Zhang, Zhizhong and Fan, Jianping and Shi, Zhongchao and Qu, Yanyun},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={11218--11228},
  year={2023}

Contact

[email protected]; [email protected].

Acknowledgements

The code is implemented based on ADCA(ACMMM2022), PGM(CVPR2023). We sincerely thank all researchers for their high-quality works.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages