Pattern Recognition from One Example by Chopping

@inproceedings{Fleuret2005PatternRF,
  title={Pattern Recognition from One Example by Chopping},
  author={François Fleuret and Gilles Blanchard},
  booktitle={NIPS},
  year={2005}
}
We investigate the learning of the appearance of an object fr om a single image of it. Instead of using a large number of pictures of the obj ct to recognize, we use a labeled reference database of pictures o f other objects to learn invariance to noise and variations in pose and illumination. This acquired knowledge is then used to predict if two pictur es of new objects, which do not appear on the training pictures, actua lly display the same object. We propose a generic scheme called… CONTINUE READING
Highly Cited
This paper has 27 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 19 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 13 references

A Bayesian approach to unsupe rvised one-shot learning of object categories

  • F. Li, R. Fergus, P. Perona
  • Proceedings of ICCV , volume 2, page 1134
  • 2003
1 Excerpt

Viola . Learning from one example through shared densities on transforms

  • S. A. Nene, S. K. Nayar
  • Proceedings of the IEEE conference on Computer…
  • 2000

editors

  • S. Thrun, L. Pratt
  • Learning to learn. Kluwer
  • 1997
1 Excerpt

Columbia Object Image L ibrary (COIL-100)

  • S. A. Nene, S. K. Nayar, H. Murase
  • Technical Report CUCS-006-96, Columbia University
  • 1996
1 Excerpt

Similar Papers

Loading similar papers…