- Notifications
You must be signed in to change notification settings - Fork30
zijundeng/BDRAR
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection
by Lei Zhu^, Zijun Deng^, Xiaowei Hu, Chi-Wing Fu, Xuemiao Xu, Jing Qin, and Pheng-Ann Heng (^ joint 1st authors)
This implementation is written by Zijun Deng at the South China University of Technology.
@inproceedings{zhu18b,
author = {Zhu, Lei and Deng, Zijun and Hu, Xiaowei and Fu, Chi-Wing and Xu, Xuemiao and Qin, Jing and Heng, Pheng-Ann},
title = {Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection},
booktitle = {ECCV},
year = {2018}
}
The results of shadow detection on SBU and UCF can be found atGoogle Drive.
You can download the trained model which is reported in our paper atGoogle Drive.
- Python 2.7
- PyTorch 0.4.0
- torchvision
- numpy
- Cython
- pydensecrf (here to install)
- Set the path of pretrained ResNeXt model in resnext/config.py
- Set the path ofSBU dataset in config.py
The pretrained ResNeXt model is ported from theofficial torch version,using theconvertor provided by clcarwin.You can directlydownload the pretrained model ported by me.
- Run by
python train.py
Hyper-parameters of training were gathered at the beginning oftrain.py and you can convenientlychange it as you need.
Training a model on a single GTX 1080Ti GPU takes about 40 minutes.
- Put the trained model in ckpt/BDRAR
- Run by
python infer.py