Generative versus discriminative methods for object recognition

  title={Generative versus discriminative methods for object recognition},
  author={Ilkay Ulusoy and Christopher M. Bishop},
  journal={2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)},
  pages={258-265 vol. 2}
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
Highly Influential
This paper has highly influenced 17 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 190 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 125 extracted citations

Automatic Caption Generation for News Images

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2013
View 5 Excerpts
Highly Influenced

Weakly supervised classification with bagging in fisheries acoustics

2009 IEEE International Symposium on Intelligent Signal Processing • 2009
View 5 Excerpts
Highly Influenced

Weakly supervised learning using proportion-based information: An application to fisheries acoustics

2008 19th International Conference on Pattern Recognition • 2008
View 7 Excerpts
Highly Influenced

Generic Object Recognition

View 5 Excerpts
Highly Influenced

190 Citations

Citations per Year
Semantic Scholar estimates that this publication has 190 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 12 references

Similar Papers

Loading similar papers…