HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation

This is the official code for the HGFormer (CVPR 2023)

Installation

See installation instructions.

Getting Started

See Preparing Datasets for HGFormer.

See Getting Started with HGFormer.

Pre-trained Models and Baselines

We provide a large set of baseline results and trained models available for download in the HGFormer Model Zoo.

Citing HGFormer

If you use HGFormer in your research, please use the following BibTeX entry.

@inproceedings{ding2023hgformer,
  title={HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation},
  author={Ding, Jian and Xue, Nan and Xia, Gui-Song and Schiele, Bernt and Dai, Dengxin},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={15413--15423},
  year={2023}
}

Acknowledgement

Code is largely based on Mask2Former (https://github.com/facebookresearch/Mask2Former).