Abstract
We present a method for generating object segmentationproposals from groups of superpixels. The goal is to pro-pose accurate segmentations for all objects of an image.The proposed object hypotheses can be used as input toobject detection systems and thereby improve efficiency byreplacing exhaustive search. The segmentations are gener-ated in a class-independent manner and therefore the com-putational cost of the approach is independent of the num-ber of object classes. Our approach combines both globaland local search in the space of sets of superpixels. The local search is implemented by greedily merging adjacent pairs of superpixels to build a bottom-up segmentation hierarchy. The regions from such a hierarchy directly providea part of our region proposals. The global search provides the other part by performing a set of graph cut segmentations on a superpixel graph obtained from an intermediate level of the hierarchy. The parameters of the graph cut problems are learnt in such a manner that they provide complementary sets of regions. Experiments with Pascal VOC images show that we reach state-of-the-art with greatly reduced computational cost.