General surgery vision transformer (GSViT)

Code repository for paper: "General surgery vision transformer: A video pre-trained foundation model for general surgery"

Please download the GSViT model from here: https://livejohnshopkins-my.sharepoint.com/:u:/g/personal/sschmi46_jh_edu/ERwRJGVUHRtKqvnSabuyKPgBfM8Hhe_Ks0EPTXg97nZ1Qw?e=hh02un

Procedure-specific fine-tuned models to be released in the same folder ASAP. Please email me sschmi46@jhu.edu if you need access to these now.

Link to the paper: General surgery vision transformer: A video pre-trained foundation model for general surgery

Please cite the following:

@article{schmidgall2024general,
  title={General surgery vision transformer: A video pre-trained foundation model for general surgery},
  author={Schmidgall, Samuel and Kim, Ji Woong and Jopling, Jeffery and Krieger, Axel},
  journal={arXiv preprint arXiv:2403.05949},
  year={2024}
}