Learning hierarchical similarity metrics

Nakul Verma, Dhruv Mahajan, Sundararajan Sellamanickam, Vinod Nair
2012 2012 IEEE Conference on Computer Vision and Pattern Recognition  
Categories in multi-class data are often part of an underlying semantic taxonomy. Recent work in object classification has found interesting ways to use this taxonomy structure to develop better recognition algorithms. Here we propose a novel framework to learn similarity metrics using the class taxonomy. We show that a nearest neighbor classifier using the learned metrics gets improved performance over the best discriminative methods. Moreover, by incorporating the taxonomy, our learned
more » ... can also help in some taxonomy specific applications. We show that the metrics can help determine the correct placement of a new category that was not part of the original taxonomy, and can provide effective classification amongst categories local to specific subtrees of the taxonomy. 2. In a hierarchical setting, local representations make it possible for the children to share the representation (or
doi:10.1109/cvpr.2012.6247938 dblp:conf/cvpr/VermaMSN12 fatcat:ktrw3nsvg5hlbjafk2pefd23ha