@article{convnetvstransformersupervisedvsclip,
  title = {ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy},
  author = {Kirill Vishniakov and Zhiqiang Shen and Zhuang Liu},
  year = {2023},
  eprint = {2311.09215},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.09215v3},
}