PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

An invariant large margin nearest neighbour classifier
Mudigonda Pawan Kumar, Philip Torr and Andrew Zisserman
In: ICCV 2007, 14-20 Oct 2007, Rio de Janeiro, Brazil.

Abstract

The k-nearest neighbour (kNN) rule is a simple and effective method for multi-way classification that is much used in Computer Vision. However, its performance depends heavily on the distance metric being employed. The recently proposed large margin nearest neighbour (LMNN) classifier learns a distance metric for kNN classification and thereby improves its accuracy. Learning involves optimizing a convex problem using semidefinite programming (SDP). We extend the LMNN framework to incorporate knowledge about invariance of the data. The main contributions of our work are three fold: (i) Invariances to multivariate polynomial transformations are incorporated without explicitly adding more training data during learning - these can approximate common transformations such as rotations and affinities; (ii) the incorporation of different regularizers on the parameters being learnt; and (iii) for all these variations, we show that the distance metric can still be obtained by solving a convex SDP problem. We call the resulting formulation invariant LMNN (ILMNN) classifier. We test our approach to learn a metric for matching (i) feature vectors from the standard Iris dataset; and (ii) faces obtained from TV video (an episode of `Buffy the Vampire Slayer'). We compare our method with the state of the art classifiers and demonstrate improvements.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:3048
Deposited By:Mudigonda Pawan Kumar
Deposited On:21 September 2007