SCaLE: Supervised and Cascaded Laplacian Eigenmaps for Visual Object Recognition Based on Nearest Neighbors

Ruobing Wu, Yizhou Yu, Wenping Wang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 867-874

Abstract


Recognizing the category of a visual object remains a challenging computer vision problem. In this paper we develop a novel deep learning method that facilitates examplebased visual object category recognition. Our deep learning architecture consists of multiple stacked layers and computes an intermediate representation that can be fed to a nearest-neighbor classifier. This intermediate representation is discriminative and structure-preserving. It is also capable of extracting essential characteristics shared by objects in the same category while filtering out nonessential differences among them. Each layer in our model is a nonlinear mapping, whose parameters are learned through two sequential steps that are designed to achieve the aforementioned properties. The first step computes a discrete mapping called supervised Laplacian Eigenmap. The second step computes a continuous mapping from the discrete version through nonlinear regression. We have extensively tested our method and it achieves state-of-the-art recognition rates on a number of benchmark datasets.

Related Material


[pdf]
[bibtex]
@InProceedings{Wu_2013_CVPR,
author = {Wu, Ruobing and Yu, Yizhou and Wang, Wenping},
title = {SCaLE: Supervised and Cascaded Laplacian Eigenmaps for Visual Object Recognition Based on Nearest Neighbors},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}
}