---
license: apache-2.0
tags:
- self-supervised learning
- vision
- SiT
inference: false

---

# Model description

SiT is a self-supervised learning model that combines masked image modeling and contrastive learning. The model is trained on ImageNet-1K.


# Model Sources

- https://github.com/Sara-Ahmed/SiT
- https://arxiv.org/abs/2104.03602


# Model Card Authors 
Sara Atito, Muhammad Awais, Josef Kittler

# How to use

```python
from modeling_sit import ViTSiTForPreTraining
# reload
model = ViTSiTForPreTraining.from_pretrained("erow/SiT")
```

# BibTeX entry and citation info
```
@inproceedings{atito2023sit,
  title={SiT is all you need},
  author={Atito, Sara and Awais, Muhammed and Nandam, Srinivasa and Kittler, Josef},
  booktitle={2023 IEEE International Conference on Image Processing (ICIP)},
  pages={2125--2129},
  year={2023},
  organization={IEEE}
}
```