2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06) (2006)
New York, NY
June 17, 2006 to June 22, 2006
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CVPR.2006.100
Raia Hadsell , New York University
Sumit Chopra , New York University
Yann LeCun , New York University
Dimensionality reduction involves mapping a set of high dimensional input points onto a low dimensional manifold so that 'similar" points in input space are mapped to nearby points on the manifold. We present a method - called Dimensionality Reduction by Learning an Invariant Mapping (DrLIM) - for learning a globally coherent nonlinear function that maps the data evenly to the output manifold. The learning relies solely on neighborhood relationships and does not require any distancemeasure in the input space. The method can learn mappings that are invariant to certain transformations of the inputs, as is demonstrated with a number of experiments. Comparisons are made to other techniques, in particular LLE.
S. Chopra, Y. LeCun and R. Hadsell, "Dimensionality Reduction by Learning an Invariant Mapping," 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)(CVPR), New York, NY, 2006, pp. 1735-1742.