This is a Pytorch implementation of our paper "Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation".

AAAI2022 [arxiv]

• python3.7
• pytorch>=1.5.0
• cuda10.2

GTA5

Synthia

Cityscapes

Dark Zurich

1. The source only model for GTA5 and Synthia are provided by AdaptSegNet.
2. For day-to-night adaptation, please download the model pretrained on Cityscapes here.

Download these pretrained models and put them into the pretrained_model folder.

Modify the all data paths in the train_config.py and test_config.py.

bash run.sh

Part of our code is from MixStyle and AdaptSegNet. We gratefully thank the authors for their great work. Also thank the authors of ASM for introducing this one-shot UDA setting.

If you think this paper is useful for your research, please cite our paper:

@inproceedings{wu2021style,
  title={Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation},
  author={Wu, Xinyi and Wu, Zhenyao and Lu, Yuhang and Ju, Lili and Wang, Song},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  year={2022}
}