Official PyTorch implementation of the paper "Dataset Distillation with Neural Characteristic Function" (NCFM) in CVPR 2025.

• [2025/03/02] The code of our paper has been released.
• [2025/02/27] Our NCFM paper has been accepted to CVPR 2025 (Rating: 555). Thanks!

Here's an overview of the process behind our Neural Characteristic Function Matching (NCFM) method:

To get started with NCFM, follow the installation instructions below.

1. Clone the repo

git clone https://github.com/gszfwsb/NCFM.git

2. Install dependencies

pip install -r requirements.txt

3. Pretrain the models yourself, or download the pretrained_models from huggingface.

cd pretrain
torchrun --nproc_per_node={n_gpus} --nnodes=1 pretrain_script.py --gpu={gpu_ids} --config_path=../config/{ipc}/{dataset}.yaml

4. Condense

cd condense 
torchrun --nproc_per_node={n_gpus} --nnodes=1 condense_script.py --gpu={gpu_ids} --ipc={ipc} --config_path=../config/{ipc}/{dataset}.yaml

5. Evaluation or or download the condensed dataset from huggingface

cd evaluation 
torchrun --nproc_per_node={n_gpus} --nnodes=1 evaluation_script.py --gpu={gpu_ids} --ipc={ipc} --config_path=../config/{ipc}/{dataset}.yaml --load_path={distilled_dataset.pt}

1. CIFAR-10

#ipc50
cd condense
torchrun --nproc_per_node=8 --nnodes=1 --master_port=34153 condense_script.py --gpu="0,1,2,3,4,5,6,7" --ipc=50 --config_path=../config/ipc50/cifar10.yaml

2. CIFAR-100

#ipc10
cd condense
torchrun --nproc_per_node=8 --nnodes=1 --master_port=34153 condense_script.py --gpu="0,1,2,3,4,5,6,7" --ipc=10 --config_path=../config/ipc10/cifar100.yaml

If you have any questions, please contact Shaobo Wang(shaobowang1009@sjtu.edu.cn).

If you find NCFM useful for your research and applications, please cite using this BibTeX:

@inproceedings{wang2025NCFM,
      title={Dataset Distillation with Neural Characteristic Function: A Minmax Perspective}, 
      author={Shaobo Wang and Yicun Yang and Zhiyuan Liu and Chenghao Sun and Xuming Hu and Conghui He and Linfeng Zhang},
 booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
  year={2025}
}

We sincerely thank the developers of the following projects for their valuable contributions and inspiration: MTT, DATM, DC/DM, IDC, SRe2L, RDED, DANCE. We draw inspiration from these fantastic projects!