• This is the sample code of saliency detection for 2017 cvpr paper [Instance-Level Salient Object Segmentation] by Guanbin Li, Yuan Xie, Liang Lin and Yizhou Yu
• This code is tested on MATLAB 2014b on Ubuntu14.04
• For more information, please visit our project page (http://www.sysu-hcp.net/instance-level-salient-object-segmentation)

This code includes

• 'deeplab-caffe': the Caffe toolbox for Multiscale Refinement Network (MSRNet)
• 'models_prototxts': pre-trained models and prototxts
• 'code': codes to do testing
• 'data':
  • a.imgs: source images to do saliency detection
  • b.pre: predicted results

Please follow the instructions below to run the code.

• Compile the Caffe and matcaffe in the deeplab-caffe package.
• Put your own images in the data/imgs directory
• Download the pretrained MSRNet-VGG models by running the script

  ./models_prototxts/get_msrnet-vgg_model.sh

• Generate saliency map by running the matlab code

  ./code/demo.m

If you find this useful, please cite our work as follows:

@inproceedings{MSRNet2017object,
  title={Instance-Level Salient Object Segmentation},
  author={Guanbin Li, Yuan Xie, Liang Lin and Yizhou Yu},
  booktitle={CVPR},
  year={2017}
}

Please contact "[email protected]" if any questions with the code.