CF-Caffe

Caffe designed for Deep Context Features

Basic Citation

If you use CF-Caffe, please cite:

@InProceedings{Hu_2018_CVPR,
     author = {Hu, Xiaowei and Zhu, Lei and Fu, Chi-Wing and Qin, Jing and Heng, Pheng-Ann},
     title = {Direction-Aware Spatial Context Features for Shadow Detection},
     booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages={7454--7462},
     year = {2018}
}

@article{hu2018direction,
     author = {Hu, Xiaowei and Fu, Chi-Wing and Zhu, Lei and Qin, Jing and Heng, Pheng-Ann},
     title = {Direction-aware Spatial Context Features for Shadow Detection and Removal},
     journal={arXiv preprint arXiv:1805.04635},
     year = {2018}
}

@article{jia2014caffe,
     author = {Jia, Yangqing and Shelhamer, Evan and Donahue, Jeff and Karayev, Sergey and Long, Jonathan and Girshick, Ross and Guadarrama, Sergio and Darrell, Trevor},
     title = {Caffe: Convolutional Architecture for Fast Feature Embedding},
     journal = {arXiv preprint arXiv:1408.5093},
     year = {2014}
}

Installation

1. Clone this repository.

   git clone https://github.com/xw-hu/CF-Caffe.git

2. Build CF-Caffe

   *This model is tested on Ubuntu 16.04, CUDA 8.0.

   Follow the Caffe installation instructions here: http://caffe.berkeleyvision.org/installation.html

   make all -jXX

3. If you want to use MATLAB or Python:

   make matcaffe
   make pycaffe

Models

If you use these models, please cite their papers accordingly.

1. Segmentation models in examples/segmentation/:

   Deeplab v1, Deeplab v3, Deeplab v3 plus, PSPNet, PSANet, Non-local Network (FPN based).

2. This version of Caffe is used in:

DSC

@InProceedings{Hu_2018_CVPR,
     author = {Hu, Xiaowei and Zhu, Lei and Fu, Chi-Wing and Qin, Jing and Heng, Pheng-Ann},
     title = {Direction-Aware Spatial Context Features for Shadow Detection},
     booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages={7454--7462},
     year = {2018}
}

@article{hu2018direction,
     author = {Hu, Xiaowei and Fu, Chi-Wing and Zhu, Lei and Qin, Jing and Heng, Pheng-Ann},
     title = {Direction-aware Spatial Context Features for Shadow Detection and Removal},
     journal={arXiv preprint arXiv:1805.04635},
     year = {2018}
}

GNLB

@article{zhu2018saliency,
     author = {Zhu, Lei and Hu, Xiaowei and Fu, Chi-Wing and Qin, Jing and Heng, Pheng-Ann},
     title = {Saliency-aware Texture Smoothing},
     journal={IEEE Transactions on Visualization and Computer Graphics},
     year = {2018}
}

RADF

@inproceedings{hu18recurrently,
     author = {Hu, Xiaowei and Zhu, Lei and Qin, Jing and Fu, Chi-Wing and Heng, Pheng-Ann},
     title = {Recurrently Aggregating Deep Features for Salient Object Detection},
     booktitle = {AAAI},
     pages={6943--6950},
     year = {2018}
}