This is the Pytorch implementation of our NeurIPS 2020 Oral paper Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation.
pip install -r ./requirements.txt
We test our codes with two NVIDIA Tesla V100 (32G) GPU cards.
See experiments/data/
Following general practice, our training starts from ResNet-101 backbone pretrained on ImageNet. Please download the weight file and put it under the model directory.
For GTAV to CityScapes:
CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node=2 --use_env ./tools/train.py --cfg ./experiment/config/g2c_train.yaml --exp_name g2c
For SYNTHIA to CityScapes:
CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node=2 --use_env ./tools/train.py --cfg ./experiment/config/s2c_train.yaml --exp_name s2c
You can also use the shell scripts provided under directory experiment/scripts/train.sh to train your model.
For GTAV to CityScapes:
CUDA_VISIBLE_DEVICES=0,1 python ./tools/test.py --cfg ./experiment/config/g2c_test.yaml --weights ${PATH_TRAINED_WEIGHTS} --exp_name g2c_test
For SYNTHIA to CityScapes:
CUDA_VISIBLE_DEVICES=0,1 python ./tools/test.py --cfg ./experiment/config/s2c_test.yaml --weights ${PATH_TRAINED_WEIGHTS} --exp_name s2c_test
You can also use the shell scripts provided under directory experiment/scripts/test_normal.sh to evaluate your model.
Our trained model for both tasks can be downloaded from PLCA-trained-model with test mIoU 47.8% and 46.9% (16 classes) respectively.
Please cite our paper if you use our code in your research:
@inproceedings{kang2020pixel,
title={Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation},
author={Kang, Guoliang and Wei, Yunchao and Yang, Yi and Zhuang, Yueting and Hauptmann, Alexander G},
booktitle={NeurIPS},
year={2020}
}
If you have any questions, please contact me via kgl.prml@gmail.com.
torchvision