Discriminative Structure Learning of Hierarchical Representations for Object Detection

A variety of flexible models have been proposed to detect objects in challenging real world scenes. Motivated by some of the most successful techniques, we propose a hierarchical multi-feature representation and automatically learn flexible hierarchical object models for a wide variety of object classes. To that end we not only rely on automatic selection of relevant individual features, but go beyond previous work by automatically selecting and modeling complex, long-range feature couplings within this model. To achieve this generality and flexibility our work combines structure learning in conditional random fields and discriminative parameter learning of classifiers using hierarchical features. We adopt an efficient gradient based heuristic for model selection and carry it forward to discriminative, multidimensional selection of features and their couplings for improved detection performance. Experimentally we consistently outperform the currently leading method on a...

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Paul Schnitzspan (TU Darmstadt), Mario Fritz (University of California, Berkeley), Stefan Roth (TU Darmstadt), Bernt Schiele (TU Darmstadt)
• Keywords: Computer Vision, CVPR 2009, Object Detection, Structure Learning Of Hierarchical Representations