Sciweavers

Share
ICCV
2007
IEEE

Fast Pixel/Part Selection with Sparse Eigenvectors

9 years 7 months ago
Fast Pixel/Part Selection with Sparse Eigenvectors
We extend the "Sparse LDA" algorithm of [7] with new sparsity bounds on 2-class separability and efficient partitioned matrix inverse techniques leading to 1000-fold speed-ups. This mitigates the O(n4 ) scaling that has limited this algorithm's applicability to vision problems and also prioritizes the less-myopic backward elimination stage by making it faster than forward selection. Experiments include "sparse eigenfaces" and gender classification on FERET data as well as pixel/part selection for OCR on MNIST data using Bayesian (GP) classification. SparseLDA is an attractive alternative to the more demanding Automatic Relevance Determination. State-of-the-art recognition is obtained while discarding the majority of pixels in all experiments. Our sparse models also show a better fit to data in terms of the "evidence" or marginal likelihood.
Bernard Moghaddam, Yair Weiss, Shai Avidan
Added 14 Oct 2009
Updated 30 Oct 2009
Type Conference
Year 2007
Where ICCV
Authors Bernard Moghaddam, Yair Weiss, Shai Avidan
Comments (0)
books