Cross Contrasting Feature Perturbation for Domain Generalization (ICCV'23)

Official PyTorch implementation of Cross Contrasting Feature Perturbation for Domain Generalization.

Chenming Li, Daoan Zhang, Wenjian Huang, Jianguo Zhang

Note that this project is built upon DomainBed@3fe9d7.

Preparation

Dependencies

pip install -r requirements.txt

Download the datasets:

python -m domainbed.scripts.download \
       --data_dir=Your_data_dir

Train a model:

python train.py --data_dir Your_data_dir --test_envs 0 --algorithm CCFP --dataset PACS

Launch a sweep:

python sweep.py launch --data_dir=Your_data_dir\
       --output_dir=Your_output_dir\
       --command_launcher multi_gpu\
       --algorithms CCFP\
       --datasets PACS\
       --n_hparams 5\
       --n_trials 3

Citation

@inproceedings{li2023cross,
  title={Cross contrasting feature perturbation for domain generalization},
  author={Li, Chenming and Zhang, Daoan and Huang, Wenjian and Zhang, Jianguo},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={1327--1337},
  year={2023}
}