Repository files navigation

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)

1. Set the path of pretrained ResNeXt model in resnext/config.py
2. 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.

1. Run bypython 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.

1. Put the trained model in ckpt/BDRAR
2. Run bypython infer.py