nips nips2006 nips2006-185 nips2006-185-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Aharon B. Hillel, Daphna Weinshall
Abstract: We address the problem of sub-ordinate class recognition, like the distinction between different types of motorcycles. Our approach is motivated by observations from cognitive psychology, which identify parts as the defining component of basic level categories (like motorcycles), while sub-ordinate categories are more often defined by part properties (like ’jagged wheels’). Accordingly, we suggest a two-stage algorithm: First, a relational part based object model is learnt using unsegmented object images from the inclusive class (e.g., motorcycles in general). The model is then used to build a class-specific vector representation for images, where each entry corresponds to a model’s part. In the second stage we train a standard discriminative classifier to classify subclass instances (e.g., cross motorcycles) based on the class-specific vector representation. We describe extensive experimental results with several subclasses. The proposed algorithm typically gives better results than a competing one-step algorithm, or a two stage algorithm where classification is based on a model of the sub-ordinate class. 1
[1] S. Agarwal and D. Roth. Learning a sparse representation for object detection. In ECCV, 2002.
[2] A. Bar-Hillel, T. Hertz, and D. Weinshall. Efficient learning of relational object class models. In ICCV, 2005.
[3] G.C. Cawley. MATLAB SVM Toolbox [http://theoval.sys.uea.ac.uk/˜gcc/svm/toolbox].
[4] P. Feltzenswalb and D. Hutenlocher. Pictorial structures for object recognition. IJCV, 61:55–79, 2005.
[5] R. Fergus, P. Perona, and A. Zisserman. Object class recognition by unsupervised scale invariant learning. In CVPR, 2003.
[6] R. Fergus, P. Perona, and A. Zisserman. A sparse object category model for efficient learning and exhaustive recognition. In CVPR, 2005.
[7] AD. Holub, M. Welling, and P. Perona. Combining generative models and fisher kernels for object class recognition. In International Conference on Computer Vision (ICCV), 2005.
[8] T. Kadir and M. Brady. Scale, saliency and image description. IJCV, 45(2):83–105, November 2001.
[9] B. Leibe, A. Leonardis, and B. Schiele. Combined object categorization and segmentation with an implicit shape model. In ECCV workshop on statistical learning in computer vision, 2004.
[10] Fritz M., Leibe B., Caputo B., and Schiele B. Integrating representative and discriminative models for object category detection. In ICCV, pages 1363–1370, 2005.
[11] E. Rosch, C.B. Mervis, W.D. Gray, D.M. Johnson, and P. Boyes-Braem. Basic objects in natural categories. Cognitive Psychology, 8:382–439, 1976.
[12] R.E. Schapire and Y. Singer. Improved boosting using confidence-rated predictions. Machine Learning, 37(3):297–336, 1999.
[13] B. Tversky and K. Hemenway. Objects, parts, and categories. Journal of Experimental Psychology: General, 113(2):169–197, 1984.