StyP-Boost: A Bilinear Boosting Algorithm for Learning Style-Parameterized Classifiers

We introduce a novel bilinear boosting algorithm, which extends the multi-class boosting framework of JointBoost to optimize a bilinear objective function. This allows style parameters to be introduced to aid classification, where style is any factor which the classes vary with systematically, modeled by a vector quantity. The algorithm allows learning to take place across different styles. We apply this Style Parameterized Boosting framework (StyP-Boost) to two object class segmentation tasks: road surface segmentation and general scene parsing. In the former the style parameters represent global surface appearance, and in the latter the probability of belonging to a scene-class. We show how our framework improves on 1) learning without style, and 2) learning independent classifiers within each style. Further, we achieve state-of-the-art results on the Corel database for scene parsing.

[1]  Roberto Cipolla,et al.  Semantic texton forests for image categorization and segmentation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Christopher K. I. Williams,et al.  Pascal Visual Object Classes Challenge Results , 2005 .

[3]  Antonio Torralba,et al.  Using the forest to see the trees: exploiting context for visual object detection and localization , 2010, CACM.

[4]  Jianguo Zhang,et al.  The PASCAL Visual Object Classes Challenge , 2006 .

[5]  Miguel Á. Carreira-Perpiñán,et al.  Multiscale conditional random fields for image labeling , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[6]  Richard S. Zemel,et al.  Learning and Incorporating Top-Down Cues in Image Segmentation , 2006, ECCV.

[7]  C. V. Jawahar,et al.  Scene Text Recognition using Higher Order Language Priors , 2009, BMVC.

[8]  Charless C. Fowlkes,et al.  Bilinear classifiers for visual recognition , 2009, NIPS.

[9]  Ali Farhadi,et al.  A latent model of discriminative aspect , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[10]  Joshua B. Tenenbaum,et al.  Separating Style and Content with Bilinear Models , 2000, Neural Computation.

[11]  Antonio Torralba,et al.  Sharing Visual Features for Multiclass and Multiview Object Detection , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Philip H. S. Torr,et al.  Combining Appearance and Structure from Motion Features for Road Scene Understanding , 2009, BMVC.

[13]  Y. Freund,et al.  Discussion of the Paper \additive Logistic Regression: a Statistical View of Boosting" By , 2000 .

[14]  Pushmeet Kohli,et al.  Associative hierarchical CRFs for object class image segmentation , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[15]  Antonio Criminisi,et al.  TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation , 2006, ECCV.

[16]  Tsuhan Chen,et al.  Learning class-specific affinities for image labelling , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Antonio Torralba,et al.  Contextual Priming for Object Detection , 2003, International Journal of Computer Vision.

[18]  Zhuowen Tu,et al.  Image Parsing: Unifying Segmentation, Detection, and Recognition , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.