Tangent Vector Kernels for Invariant Image Classification with SVMs. Pozdnoukhov, A. & Bengio, S. In International Conference on Pattern Recognition, ICPR, volume 3, pages 486–489, 2004.
Tangent Vector Kernels for Invariant Image Classification with SVMs [link]Paper  abstract   bibtex   
This paper presents an application of the general sample-to-object approach to the problem of invariant image classification. The approach results in defining new SVM kernels based on tangent vectors that take into account prior information on known invariances. Real data of face images are used for experiments. The presented approach integrates virtual sample and tangent distance methods. We observe a significant increase in performance with respect to standard approaches. The experiments also illustrate (as expected) that prior knowledge becomes more important as the amount of training data decreases.
@inproceedings{pozdnoukhov:2004:icpr,
  author =   {A. Pozdnoukhov and S. Bengio},
  title =    {Tangent Vector Kernels for Invariant Image Classification with {SVMs}},
  booktitle =  {International Conference on Pattern Recognition, {ICPR}},
  year =   2004,
  volume = 3,
  pages = {486--489},
  url = {publications/ps/pozdnoukhov_2004_icpr.ps.gz},
  pdf = {publications/pdf/pozdnoukhov_2004_icpr.pdf},
  djvu = {publications/djvu/pozdnoukhov_2004_icpr.djvu},
  original = {2004/tangent_icpr},
  idiap = {publications/pdf/rr03-75.pdf},
  topics = {kernel},
  web = {http://dx.doi.org/10.1109/ICPR.2004.1334572},
  abstract = {This paper presents an application of the general sample-to-object approach to the problem of invariant image classification. The approach results in defining new SVM kernels based on tangent vectors that take into account prior information on known invariances. Real data of face images are used for experiments. The presented approach integrates virtual sample and tangent distance methods. We observe a significant increase in performance with respect to standard approaches. The experiments also illustrate (as expected) that prior knowledge becomes more important as the amount of training data decreases.},
  categorie = {C},
}

Downloads: 0