Learning Deep Nearest Neighbor Representations Using Differentiable Boundary Trees

Abstract

Nearest neighbor (k-NN) methods have been gaining popularity in recent years in light of advances in hardware and efficiency of algorithms. There is a plethora of methods to choose from today, each with their own advantages and disadvantages. One requirement shared between all k-NN based methods is the need for a good representation and distance measure… (More)

Topics

9 Figures and Tables

Blog articles referencing this paper

Slides referencing similar topics