Publication Search Form

Keywords

Authors

Year

We found publication with these paramters.

Scalable graph Laplacian kernels for object classification from very few examples

Hong Chang, Dit-Yan Yeung
Classification with very few labeled examples per class is a challenging problem in machine learning and pattern recognition. While there have been some attempts to address this problem in the context of specific applications, e.g., face recognition, very little work has been done so far on the problem under more general object classification settings. In this paper, we propose a graph-based approach to the problem. Based on a robust path-based similarity measure proposed recently, we construct a weighted graph using the robust path-based similarities as edge weights. A kernel matrix, called graph laplacian kernel, is then defined based on the graph Laplacian. With the kernel matrix, any kernel-based classifier can be used for subsequent classification. Our method can handle relatively large data sets by applying either neighborhood propagation or kernel matrix factorization. We demonstrate the use of a kernel nearest neighbor classifier on some synthetic and real-world data sets, showing that our method can successfully solve some difficult classification tasks with only very few labeled examples
To appear in IEEE transactions on image processing
2007
2007/024