Generative versus discriminative methods for object recognition

@article{Ulusoy2005GenerativeVD,
  title={Generative versus discriminative methods for object recognition},
  author={I. Ulusoy and Charles M. Bishop},
  journal={2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)},
  year={2005},
  volume={2},
  pages={258-265 vol. 2}
}
  • I. Ulusoy, Charles M. Bishop
  • Published 2005
  • Computer Science
  • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 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 paper we introduce new generative and discriminative models for object detection and classification based on weakly labelled training data… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Comparison of Generative and Discriminative Techniques for Object Detection and Classification
    25
    Principled Hybrids of Generative and Discriminative Models
    307
    A Discriminative Framework for Object Recognition
    Discriminative Training of Hyper-feature Models for Object Identification
    36
    Patch-based Object Recognition Using Discriminatively Trained Gaussian Mixtures
    30
    Efficient Learning of Relational Object Class Models
    64
    A mixed generative-discriminative framework for pedestrian classification
    105
    Hybrids of generative and discriminative methods for machine learning
    10

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 14 REFERENCES
    Object class recognition by unsupervised scale-invariant learning
    2470
    Selection of scale-invariant parts for object class recognition
    346
    Object recognition with informative features and linear classification
    295
    Visual categorization with bags of keypoints
    4721
    Saliency, Scale and Image Description
    1203
    Matching Words and Pictures
    1716
    The Helmholtz Machine
    1002
    Scale & Affine Invariant Interest Point Detectors
    3740
    Neural Networks for Pattern Recognition
    12761