Official implementation of the paper "SYNC-CLIP: Synthetic Data Make CLIP Generalize Better in Data-Limited Scenarios".
If you find our work, this repository, or pretrained models useful, please consider giving a star ⭐ and citation.
@article{liu2023sync,
title={SYNC-CLIP: Synthetic Data Make CLIP Generalize Better in Data-Limited Scenarios},
author={Liu, Mushui and He, Weijie and Lu, Ziqian and Yu, Yunlong},
journal={arXiv preprint arXiv:2312.03805},
year={2023}
}
If you have any questions, please create an issue on this repository or contact at lms@zju.edu.cn.
Our code is based on MaPLe, along with Co-CoOp and CoOp repository. We thank the authors for releasing their code. If you use our model and code, please consider citing these works as well.