(ECCV-W, 2018) Segmentations using MASON
Switch branches/tags
Nothing to show
Clone or download
Latest commit bc9215e Feb 18, 2018
Permalink
Failed to load latest commit information.
data Update Jan 16, 2018
lib Initial Commit Jan 12, 2018
model Initial Commit Dec 8, 2017
LICENSE Initial Commit Nov 5, 2017
README.md Update README.md Feb 18, 2018
segment_image.py Update Jan 16, 2018
semi-supervised-SS.py Update Jan 16, 2018

README.md

Unsupervised Segmentation using MASON

Unsupervised Segmentation of Images

Installation

  1. Clone this repository
git clone https://github.com/JosephKJ/MASON

Let's call the directory as ROOT

  1. Clone the Caffe repository
cd $ROOT
git clone https://github.com/Microsoft/caffe.git

[optional]

cd caffe
git reset --hard 1a2be8e
  1. Setup CAFFE

  2. Get the ImageNet pretrained VGG-16 network(caffemodel only) and place it in ./model folder.

caffemodel_url: http://www.robots.ox.ac.uk/~vgg/software/very_deep/caffe/VGG_ILSVRC_16_layers.caffemodel

Demo

You can run python segment_image.py.

This script will take the image located in ./data/demo/2007_000363.jpg, computes the objectness heatmap, uses it with GrabCut and gets the result displayed on screen. (NB: This method doesnot require any bounding box annotation.)

Output alt text (Legend: Input image -- Objectness heat map -- Segmentation using MASON and GrabCut -- Segmentation using GrabCut alone)

semi-supervised-SS.py expects bounding box information from a dataset. The code can work out of the box with Pascal VOC dataset.