Co-segmentation by Composition
Alon Faktor,
Michal Irani
This webpage presents the paper Co-segmentation by Composition (ICCV 2013).
Paper [PDF]
Abstract
Given a set of images which share an object from the
same semantic category, we would like to co-segment the
shared object. We define ‘good’ co-segments to be ones
which can be easily composed (like a puzzle) from large
pieces of other co-segments, yet are difficult to compose
from remaining image parts. These pieces must not only
match well but also be statistically significant (hard to compose
at random). This gives rise to co-segmentation of objects
in very challenging scenarios with large variations in
appearance, shape and large amounts of clutter. We further
show how multiple images can collaborate and “score”
each others’ co-segments to improve the overall fidelity and
accuracy of the co-segmentation. Our co-segmentation can
be applied both to large image collections, as well as to very
few images (where there is too little data for unsupervised
learning). At the extreme, it can be applied even to a single
image, to extract its co-occurring objects. Our approach
obtains state-of-the-art results on benchmark datasets. We
further show very encouraging co-segmentation results on
the challenging PASCAL-VOC dataset.
Code can be downloaded here
Results
Co-segmentation Results + ground truth on iCoseg dataset [ZIP]
Co-segmentation Results + ground truth on MSRC dataset [ZIP]
Co-segmentation Results + ground truth on PASCAL dataset [ZIP]
Co-segmentation Results + ground truth on Internet dataset (Rubinstein et al CVPR'13) - contact me personally
Numerical Results per class on iCoseg dataset [PDF]
Numerical Results per class on MSRC dataset [PDF]
Numerical Results per class on PASCAL dataset [PDF]