16. B. Ommer: Learning Top-Down Grouping of Compositional Hierarchies for Recognition
Compositional strategies are a means of complexity reduction for models of real world object categories. This contribution establishes a compositional hierarchy by first performing a perceptual bottom-up grouping of edge pixels to generate salient contour curves. A subsequent recursive top-down grouping yields a hierarchy of compositions. All entities in the compositional hierarchy are incorporated in a Bayesian network that couples them together by means of a shape model. The probabilistic model underlying top-down grouping as well as the shape model is learned automatically from a set of training images for the given categories. As a consequence, compositionality simplifies the learning of complex category models by building them from simple, frequently used compositions. The architecture is evaluated on the highly challenging Caltech 101 database which exhibits large intra-category variations. The proposed compositional approach shows competitive retrieval rates between 53% and 58%.