Learning Compositional Categorization Models

Abstract. This contribution proposes a compositional approach to visual object categorization of scenes. Compositions are learned from the Caltech 101 database1 intermediate abstractions of images that are semantically situated between low-level representations and the highlevel categorization. Salient regions, which are described by localized feature histograms, are detected as image parts. Subsequently compositions are formed as bags of parts with a locality constraint. After performing a spatial binding of compositions by means of a shape model, coupled probabilistic kernel classifiers are applied thereupon to establish the final image categorization. In contrast to the discriminative training of the categorizer, intermediate compositions are learned in a generative manner yielding relevant part agglomerations, i.e. groupings which are frequently appearing in the dataset while simultaneously supporting the discrimination between sets of categories. Consequently, compositionality sim...

• Type: Conference
• Year: 2006
• Where: ECCV
• Authors: Björn Ommer, Joachim M. Buhmann
• Keywords: Complex Categorization Model, Computer Vision, ECCV 2006, Final Image Categorization, Intermediate Compositions, Sharable Compositions, Visual Object Categorization