lixin666 / MSC-NET

Multi-Scale Cascade Network for Salient Object Detection

Multi-Scale Cascade Network for Salient Object Detection

by Xin Li, Fan Yang, Hong Cheng, Junyu Chen, Yuxiao Guo, Leiting Chen

Introduction

This repository is for 'Multi-Scale Cascade Network for Salient Object Detection'.

Installation

For installation, please follow the instructions of Caffe and hszhao.

The code has been tested successfully on Ubuntu 14.04 with CUDA 8.0.

Usage

1. Clone the repository:

   git clone https://github.com/lixin666/MSC-NET.git

2. Build Caffe and pycaffe:

   cd $ROOT
   cp Makefile.config.example Makefile.config
   vim Makefile.config
   make -j8 && make pycaffe

ps: You should uncomment 'WITH_PYTHON_LAYER := 1' in Makefile.config before compiling.

3. Test:

   • Test code is in folder 'test'.
   • Download trained models and put them in folder 'test/models':
     • MSCNet.caffemodel: BaiduYun or GoogleDrive
   • Put the test images in folder 'images', and run

   python test.py

   -After that, the results will be genrated in folder 'results'.

Citation

If MSCNet is useful for your research, please consider citing:

@inproceedings{li2017mscnet,
  author = {Xin Li and Fan Yang and Hong Cheng 
            and Junyu Chen and Leiting Chen},
  title = {Multi-Scale Cascade Network for Salient Object Detection},
  booktitle = {ACM MM},
  year = {2017}
}

Question

Please contact '[e-mail]'