Introduction

This repository contains the official implementation of the following papers:

• CoTNet Contextual transformer networks for visual recognition, TPAMI 2022

  

• Wave-ViT Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning, ECCV 2022

  

• Dual-ViT Dual Vision Transformer

  

Getting Started

• For Image Classification, please see classification.
• For Object Detection and Instance Segmentation, please see object_detection.
• For Semantic Segmentation, please see semantic_segmentation.

Citation

CoTNet

@article{cotnet2022,
  title={Contextual transformer networks for visual recognition},
  author={Li, Yehao and Yao, Ting and Pan, Yingwei and Mei, Tao},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2022},
  publisher={IEEE}
}

Wave-ViT

@inproceedings{wavevit2022,
    title     = {Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning},
    author    = {Yao, Ting and Pan, Yingwei and Li, Yehao and Ngo, Chong-Wah and Mei, Tao},
    booktitle = {Proceedings of the European conference on computer vision (ECCV)},
    year      = {2022},
}

Dual-ViT

@article{dualvit2022,
  title={Dual Vision Transformer},
  author={Yao, Ting and Li, Yehao and Pan, Yingwei and Wang, Yu and Zhang, Xiao-Ping and Mei, Tao},
  journal={arXiv preprint arXiv:2207.04976},
  year={2022}
}

Acknowledgements

Thanks the contribution of timm, pvt and volo.