Chang-Dong Xu, Xing-Ran Zhao, Xin Jin, Xiu-Shen Wei*
This repository is the official PyTorch implementation of paper Exploring Categorical Regularization for Domain Adaptive Object Detection. (The work has been accepted by CVPR2020)
- torch == 1.0.0
- torchvision == 0.2.0
- Python 3
This repository is developed using python 3.6.7 on Ubuntu 16.04.5 LTS. The CUDA nad CUDNN version is 9.0 and 7.4.1 respectively. We use one NVIDIA 1080ti GPU card for training and testing. Other platforms or GPU cards are not fully tested.
The pretrain backbone (vgg, resnet) and pretrain DA DET model (ICR-CCR) will be released soon.
The usage of SW-ICR-CCR is same to DA-ICR-CCR. Take DA-ICR-CCR as an example:
# install
cd DA_Faster_ICR_CCR/lib
python setup.py build develop
# to train DA-Faster-ICR-CCR on cityscape:
sh train_cityscape.sh
# To validate DA-Faster-ICR-CCR on cityscape:
python test_cityscape.pyThe data will be released soon.
If you find this code useful in your research, please consider citing us:
@article{CR-DA-DET,
title={Exploring Categorical Regularization for Domain Adaptive Object Detection},
author={Chang-Dong Xu and Xing-Ran Zhao and Xin Jin and Xiu-Shen Wei},
booktitle={CVPR},
pages={1--8},
year={2020}
}
If you have any questions about our work, please do not hesitate to contact us by emails.
Xiu-Shen Wei: [email protected]
Chang-Dong Xu: [email protected]
Xing-Ran Zhao: [email protected]
Xin Jin: [email protected]