Code for our paper Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation ICCV21
Please create and activate the following conda envrionment. To reproduce our results, please kindly create and use this environment.
# It may take several minutes for conda to solve the environment
conda update conda
conda env create -f environment.yml
conda activate corda
Code was tested on a V100 with 16G Memory.
# Train for the SYNTHIA2Cityscapes task
bash run_synthia_stereo.sh
# Train for the GTA2Cityscapes task
bash run_gta.sh
bash shells/eval_syn2city.sh
bash shells/eval_gta2city.sh
Pre-trained models are provided (Google Drive). Please put them in ./checkpoint
.
Reported Results on SYNTHIA2Cityscapes (The reported results are based on 5 runs instead of the best run.) | Method | mIoU*(13) | mIoU(16) |
---|---|---|---|
CBST | 48.9 | 42.6 | |
FDA | 52.5 | - | |
DADA | 49.8 | 42.6 | |
DACS | 54.8 | 48.3 | |
CorDA | 62.8 | 55.0 |
Please cite our work if you find it useful.
@inproceedings{wang2021domain,
title={Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation},
author={Wang, Qin and Dai, Dengxin and Hoyer, Lukas and Van Gool, Luc and Fink, Olga},
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
year={2021}
}
For questions regarding the code, please contact wang@qin.ee .