This is the official implementation of High-Resolution Transformer (HRT). We present a High-Resolution Transformer (HRT) that learns high-resolution representations for dense prediction tasks, in contrast to the original Vision Transformer that produces low-resolution representations and has high memory and computational cost. We take advantage of the multi-resolution parallel design introduced in high-resolution convolutional networks (HRNet), along with local-window self-attention that performs self-attention over small non-overlapping image windows, for improving the memory and computation efficiency. In addition, we introduce a convolution into the FFN to exchange information across the disconnected image windows. We demonstrate the effectiveness of the High-Resolution Transformeron human pose estimation and semantic segmentation tasks.

• The High-Resolution Transformer architecture:

The models are first pre-trained on ImageNet-1K dataset, and then fine-tuned on COCO val2017 dataset.

Performance on the Cityscapes dataset. The models are trained and tested with input size of 512x1024 and 1024x2048 respectively.

The models are trained with the input size of 520x520, and tested with original size.

The models are trained with input size of 520x520, and tested with original size.

The models are trained with input size of 520x520, and tested with original size. The results with window size 15x15 will be updated latter.

If you find this project useful in your research, please consider cite:

@article{YuanFHZCW21,
  title={HRT: High-Resolution Transformer for Dense Prediction},
  author={Yuhui Yuan and Rao Fu and Lang Huang and Chao Zhang and Xilin Chen and Jingdong Wang},
  booktitle={arXiv},
  year={2021}
}

This project is developed based on the Swin-Transformer, openseg.pytorch, and mmpose.

git diff-index HEAD
git subtree add -P pose <url to sub-repo> <sub-repo branch>