2007 IEEE Conference on Computer Vision and Pattern Recognition (2007)
Minneapolis, MN, USA
June 17, 2007 to June 22, 2007
Fernando De la Torre , Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213. firstname.lastname@example.org
Oriol Vinyals , Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213. email@example.com
Kernel machines (e.g. SVM, KLDA) have shown state-of-the-art performance in several visual classification tasks. The classification performance of kernel machines greatly depends on the choice of kernels and its parameters. In this paper, we propose a method to search over a space of parameterized kernels using a gradient-descent based method. Our method effectively learns a non-linear representation of the data useful for classification and simultaneously performs dimensionality reduction. In addition, we suggest a new matrix formulation that simplifies and unifies previous approaches. The effectiveness and robustness of the proposed algorithm is demonstrated in both synthetic and real examples of pedestrian and mouth detection in images.
O. Vinyals and F. De la Torre, "Learning Kernel Expansions for Image Classification," 2007 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Minneapolis, MN, USA, 2007, pp. 1-7.