Aggregating Attentional Dilated Features for Salient Object Detection
by Lei Zhu^, Jiaxing Chen^, Xiaowei Hu, Chi-Wing Fu, Xuemiao Xu, Jing Qin, and Pheng-Ann Heng (^ joint 1st authors)[paper link]
This implementation is written by Jiaxing Chen at the South China University of Technology.
Citation
@article{zhu2019aggregating,
title={Aggregating Attentional Dilated Features for Salient Object Detection},
author={Zhu, Lei and Chen, Jiaxing and Hu, Xiaowei and Fu, Chi-Wing and Xu, Xuemiao and Qin, Jing and Heng, Pheng-Ann},
journal={IEEE Transactions on Circuits and Systems for Video Technology},
year = {2019},
publisher={IEEE}
}
Saliency Map
The results of salient object detection on seven datasets (ECSSD, HKU-IS, PASCAL-S, SOD, DUT-OMRON, DUTS-TE, SOC) can be found at Google Drive.
Trained Model
You can download the trained model which is reported in our paper at Google Drive.
Requirement
- Python 2.7
- PyTorch 0.4.0
- torchvision
- numpy
- Cython
- pydensecrf (here to install)
Training
- Set the path of pretrained DenseNet model in densenet/config.py
- Set the path of DUTS dataset in config.py
- Run by
python train.py
Hyper-parameters of training were gathered at the beginning of train.py and you can conveniently change them as you need.
Testing
- Set the path of six benchmark datasets in config.py
- Put the trained model in ckpt/AADFNet
- Run by
python infer.py
Settings of testing were gathered at the beginning of infer.py and you can conveniently change them as you need.