Annbless / ViTAE

The official pytorch implementation of ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias

ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias

By Yufei Xu*, Qiming Zhang*, Jing Zhang, and Dacheng Tao, accepted by Neurips 2021.

The code and pretrained models (ViTAE and ViTAEv2) have been moved to Link. Please try it and have fun!

We have also provided the codes of using ViTAE for

Detection

Segmentation

Pose Estimation

Matting

Remote Sensing

Citing ViTAE and ViTAEv2

@article{xu2021vitae,
  title={Vitae: Vision transformer advanced by exploring intrinsic inductive bias},
  author={Xu, Yufei and Zhang, Qiming and Zhang, Jing and Tao, Dacheng},
  journal={Advances in Neural Information Processing Systems},
  volume={34},
  year={2021}
}
@article{zhang2022vitaev2,
  title={ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond},
  author={Zhang, Qiming and Xu, Yufei and Zhang, Jing and Tao, Dacheng},
  journal={arXiv preprint arXiv:2202.10108},
  year={2022}
}