Comparison of Generative and Discriminative Techniques for Object Detection and Classification

Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the distribution of the image features is modelled. Generative and discriminative methods have very different characteristics, as well as complementary strengths and weaknesses. In this chapter we introduce new generative and discriminative models for object detection and classification based on weakly labelled training data. We use these models to illustrate the relative merits of the two approaches in the context of a data set of widely varying images of non-rigid objects (animals). Our results support the assertion that neither approach alone will be sufficient for large scale object recognition, and we discuss techniques for combining the strengths of generative and discriminative approaches.

[1]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[2]  Martial Hebert,et al.  Discriminative random fields: a discriminative framework for contextual interaction in classification , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[3]  Michael Brady,et al.  Saliency, Scale and Image Description , 2001, International Journal of Computer Vision.

[4]  Geoffrey E. Hinton,et al.  The Helmholtz Machine , 1995, Neural Computation.

[5]  Ilkay Ulusoy,et al.  Generative versus discriminative methods for object recognition , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[6]  Pietro Perona,et al.  A discriminative framework for modelling object classes , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[7]  Michael I. Jordan,et al.  On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes , 2001, NIPS.

[8]  Lexing Xie,et al.  Slightly Supervised Learning of Part-Based Appearance Models , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[9]  J. Koenderink,et al.  Representation of local geometry in the visual system , 1987, Biological Cybernetics.

[10]  Daphna Weinshall,et al.  Object class recognition by boosting a part-based model , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[11]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[12]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[13]  Cordelia Schmid,et al.  Selection of scale-invariant parts for object class recognition , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[14]  Shimon Ullman,et al.  Object recognition with informative features and linear classification , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[15]  David A. Forsyth,et al.  Matching Words and Pictures , 2003, J. Mach. Learn. Res..

[16]  Guillaume Bouchard,et al.  The Tradeoff Between Generative and Discriminative Classifiers , 2004 .

[17]  Cordelia Schmid,et al.  Scale & Affine Invariant Interest Point Detectors , 2004, International Journal of Computer Vision.

[18]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .