gicd

Gradient-Induced Co-Saliency Detection
Zhao Zhang*, Wenda Jin*, Jun Xu, Ming-Ming Cheng

Prerequisites

Environments

  • PyTorch >= 1.0
  • tqdm

Pretrained model

Download gicd_ginet.pth (Baidu (05cl)/Google Drive).

Usage

  1. Configure the input root and the output root in test.sh
--param_path ./gicd_ginet.pth (pretrained model path)
--input_root your_data_root (categorize by subfolders)
--save_root your_output_root
  1. Run by
sh test.sh

Prediction results

The co-saliency maps of GICD can be found at our project home.

Citation

If you find this work is useful for your research, please cite our paper:

@inproceedings{zhang2020gicd,
 title={Gradient-Induced Co-Saliency Detection},
 author={Zhang, Zhao and Jin, Wenda and Xu, Jun and Cheng, Ming-Ming},
 booktitle={European Conference on Computer Vision (ECCV)},
 year={2020}
}

Contact

If you have any questions, feel free to contact me via zzhang🥳mail😲nankai😲edu😲cn

GitHub

https://github.com/zzhanghub/gicd