Submodular object recognition

We present a novel object recognition framework based on multiple figure-ground hypotheses with a large object spatial support, generated by bottom-up processes and mid-level cues in an unsupervised manner. We exploit the ben-efit of regression for discriminating segments ’ categories and qualities, where a regressor is trained to each category using the overlapping observations between each figure-ground segment hypothesis and the ground-truth of the tar-get category in an image. Object recognition is achieved by maximizing a submodular objective function, which maxi-mizes the similarities between the selected segments (i.e., facility locations) and their group elements (i.e., clients), penalizes the number of selected segments, and more im-portantly, encourages the consistency of object categories corresponding to maximum regression values from differ-ent category-specific regressors for the selected segments. The proposed framework achieves impressive recognition results on three benchmark datasets, including PASCAL VOC 2007, Caltech-101 and ETHZ-shape. 1