title={Swin Transformer: Hierarchical Vision Transformer using Shifted Windows},
author={Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
journal={arXiv preprint arXiv:2103.14030},
year={2021}
}
@inproceedings{liu2021swinv2,
title={Swin Transformer V2: Scaling Up Capacity and Resolution},
author={Ze Liu and Han Hu and Yutong Lin and Zhuliang Yao and Zhenda Xie and Yixuan Wei and Jia Ning and Yue Cao and Zheng Zhang and Li Dong and Furu Wei and Baining Guo},
booktitle={International Conference on Computer Vision and Pattern Recognition (CVPR)},
- Model is trained on COCO train2017 dataset and evaluated on val2017 results of `mAP(IoU=0.5:0.95)
- Base model is trained on 8x32G V100 GPU, large model on 8x80G A100
## Citations
```
@article{chen2022context,
title={Context autoencoder for self-supervised representation learning},
author={Chen, Xiaokang and Ding, Mingyu and Wang, Xiaodi and Xin, Ying and Mo, Shentong and Wang, Yunhao and Han, Shumin and Luo, Ping and Zeng, Gang and Wang, Jingdong},
journal={arXiv preprint arXiv:2202.03026},
year={2022}
}
@article{DBLP:journals/corr/abs-2111-11429,
author = {Yanghao Li and
Saining Xie and
Xinlei Chen and
Piotr Doll{\'{a}}r and
Kaiming He and
Ross B. Girshick},
title = {Benchmarking Detection Transfer Learning with Vision Transformers},
