papers AI Learner
The Github is limit! Click to go to the new site.

Volumetric Convolution: Automatic Representation Learning in Unit Ball

2019-01-03
Sameera Ramasinghe, Salman Khan, Nick Barnes

Abstract

Convolution is an efficient technique to obtain abstract feature representations using hierarchical layers in deep networks. Although performing convolution in Euclidean geometries is fairly straightforward, its extension to other topological spaces—such as a sphere ($\mathbb{S}^2$) or a unit ball ($\mathbb{B}^3$)—entails unique challenges. In this work, we propose a novel `\emph{volumetric convolution}’ operation that can effectively convolve arbitrary functions in $\mathbb{B}^3$. We develop a theoretical framework for \emph{volumetric convolution} based on Zernike polynomials and efficiently implement it as a differentiable and an easily pluggable layer for deep networks. Furthermore, our formulation leads to derivation of a novel formula to measure the symmetry of a function in $\mathbb{B}^3$ around an arbitrary axis, that is useful in 3D shape analysis tasks. We demonstrate the efficacy of proposed volumetric convolution operation on a possible use-case i.e., 3D object recognition task.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.00616

PDF

http://arxiv.org/pdf/1901.00616


Similar Posts

Comments