@article{clipitselfisastrongfinetunerachieving,
  title = {CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet},
  author = {Xiaoyi Dong and Jianmin Bao and Ting Zhang and Dongdong Chen and Shuyang Gu and Weiming Zhang and Lu Yuan and Dong Chen and Fang Wen and Nenghai Yu},
  year = {2022},
  eprint = {2212.06138},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2212.06138v1},
}