Discriminative modeling by Boosting on Multilevel Aggregates

This paper presents a new approach to discriminative modeling for classi cation and labeling. Our method, called Boosting on Multilevel Aggregates (BMA), adds a new class of hierarchical, adaptive features into boostingbased discriminative models. Each pixel is linked with a set of aggregate regions in a multilevel coarsening of the image. The coarsening is adaptive, rapid and stable. The multilevel aggregates present additional information rich features on which to boost, such as shape properties, neighborhood context, hierarchical characteristics, and photometric statistics. We implement and test our approach on three two-class problems: classifying documents in of ce scenes, buildings and horses in natural images. In all three cases, the majority, about 75%, of features selected during boosting are our proposed BMA features rather than patchbased features. This large percentage demonstrates the discriminative power of the multilevel aggregate features over conventional patch-based ...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Jason J. Corso
• Keywords: Boostingbased Discriminative Models, Computer Vision, CVPR 2008, Discriminative Modeling, Multilevel Aggregate Features, Multilevel Aggregates, Multilevel Coarsening