We randomly selected our experiment results in the two datasets as supplimentary materials. 

The OE dataset can be downloaded from : 
http://objectextraction.github.io/ 

Explanation for the results:

XXX_loc.jpg: The red object bounding box on the image is generated by our localization network.
XXX_seg.png: The grey-scale image is the object extraction result with our model.
XXX_overlap.jpg: This image shows the overlapping(yellow) of our object extraction result(red) and the groundtruth mask(green).