Arun Mukundan presents Understanding and Improving Kernel Local Descriptors

On 2019-01-18 - 11:00:00 at G205, Karlovo náměstí 13, Praha 2
We propose a multiple-kernel local-patch descriptor based on efficient match
kernels from pixel gradients. It combines two parametrizations of gradient
position and direction, each parametrization provides robustness to a different
type of patch miss-registration: polar parametrization for noise in the patch
dominant orientation detection, Cartesian for imprecise location of the feature
point. Combined with whitening of the descriptor space, that is learned with or
without supervision, the performance is significantly improved. We analyze the
effect of the whitening on patch similarity and demonstrate its semantic
meaning. Our unsupervised variant is the best performing descriptor constructed
without the need of labeled data. Despite the simplicity of the proposed
descriptor, it competes well with deep learning approaches on a number of
different tasks.
Responsible person: Petr Pošík