The Manifold Scattering Transform for High-Dimensional Point Cloud Data

06/21/2022
by   Joyce Chew, et al.
12

The manifold scattering transform is a deep feature extractor for data defined on a Riemannian manifold. It is one of the first examples of extending convolutional neural network-like operators to general manifolds. The initial work on this model focused primarily on its theoretical stability and invariance properties but did not provide methods for its numerical implementation except in the case of two-dimensional surfaces with predefined meshes. In this work, we present practical schemes, based on the theory of diffusion maps, for implementing the manifold scattering transform to datasets arising in naturalistic systems, such as single cell genetics, where the data is a high-dimensional point cloud modeled as lying on a low-dimensional manifold. We show that our methods are effective for signal classification and manifold classification tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/17/2022

Geometric Scattering on Measure Spaces

The scattering transform is a multilayered, wavelet-based transform init...
research
10/14/2020

PointManifold: Using Manifold Learning for Point Cloud Classification

In this paper, we propose a point cloud classification method based on g...
research
11/30/2020

Contagion Dynamics for Manifold Learning

Contagion maps exploit activation times in threshold contagions to assig...
research
06/27/2017

Gabor frames and deep scattering networks in audio processing

In this paper a feature extractor based on Gabor frames and Mallat's sca...
research
12/14/2019

Analytic inversion of a Radon transform on double circular arcs with applications in Compton Scattering Tomography

In this work we introduce a new Radon transform which arises from a new ...
research
03/01/2021

Pyramid Transform of Manifold Data via Subdivision Operators

Multiscale transform has become a key ingredient in many data processing...
research
03/01/2021

Exploring the high dimensional geometry of HSI features

We explore feature space geometries induced by the 3-D Fourier scatterin...

Please sign up or login with your details

Forgot password? Click here to reset