Updates | Introduction | Statement |

Classification: Please see ViTAE-VSA for Image Classification for usage detail;

Object Detection: Please see ViTAE-VSA for Object Detection for usage detail;

Semantic Segmentation: Will be released in next few days;

ViTAE & ViTAEv2: Please see ViTAE-Transformer for Image Classification, Object Detection, and Sementic Segmentation;

Matting: Please see ViTAE-Transformer for matting;

Remote Sensing: Please see ViTAE-Transformer for Remote Sensing;

19/09/2022

• The code and training logs for ViTAE-VSA have been released! The semantic segmentation and Swin+VSA will be relased in next few days.

09/07/2022

• The paper is accepted by ECCV'22!

19/04/2022

• The paper is post on arxiv! The code will be made public available once cleaned up.

This repository contains the code, models, test results for the paper VSA: Learning Varied-Size Window Attention in Vision Transformers. We design a novel varied-size window attention module which learns adaptive window configurations from data. By adopting VSA in each head independently, the model can capture long-range dependencies and rich context information from diverse windows. VSA can replace the window attention in SOTA methods and faciliate the learning on various vision tasks including classification, detection and segmentation.

If you are interested in using the VSA attention only, please consider this file in classification or the VSAWindowAttention Class in object detection applications.

ViTAEv2* denotes the version using window attention for all stages, which have much less memory requirements anc computations.

ViTAEv2* denotes the version using window attention for all stages, which have much less memory requirements anc computations.

ViTAEv2* denotes the version using window attention for all stages.

512x1024 resolution for training and testing

769x769 resolution for training and testing

Please refer to our paper for more experimental results.

This project is for research purpose only. For any other questions please contact qmzhangzz at hotmail.com yufei.xu at outlook.com.

The code base is borrowed from T2T, ViTAEv2 and Swin.

@article{zhang2022vsa,
  title={VSA: Learning Varied-Size Window Attention in Vision Transformers},
  author={Zhang, Qiming and Xu, Yufei and Zhang, Jing and Tao, Dacheng},
  journal={arXiv preprint arXiv:2204.08446},
  year={2022}
}
@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}
}
@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}
}