Spherical Convolutional Neural Networks: Stability to Perturbations in SO(3)

10/12/2020
by   Zhan Gao, et al.
0

Spherical signals are useful mathematical models for data arising in many 3-D applications such as LIDAR images, panorama cameras, and optical scanners. Successful processing of spherical signals entails architectures capable of exploiting their inherent data structure. In particular, spherical convolutional neural networks (Spherical CNNs) have shown promising performance in shape analysis and object recognition. In this paper, we focus on analyzing the properties that Spherical CNNs exhibit as they pertain to the rotational structure present in spherical signals. More specifically, we prove that they are equivariant to rotations and stable to rotation diffeomorphisms. These two properties illustrate how Spherical CNNs exploit the rotational structure of spherical signals, thus offering good generalization and faster learning. We corroborate these properties through controlled numerical experiments.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 9

02/04/2021

Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNs

Convolutional neural networks (CNNs) constructed natively on the sphere ...
04/08/2021

PDO-eS^2CNNs: Partial Differential Operator Based Equivariant Spherical CNNs

Spherical signals exist in many applications, e.g., planetary data, LiDA...
01/30/2018

Spherical CNNs

Convolutional Neural Networks (CNNs) have become the method of choice fo...
12/06/2018

Cross-Domain 3D Equivariant Image Embeddings

Spherical convolutional networks have been introduced recently as tools ...
02/11/2019

Gauge Equivariant Convolutional Networks and the Icosahedral CNN

The idea of equivariance to symmetry transformations provides one of the...
12/17/2018

Quaternion Convolutional Neural Networks for Detection and Localization of 3D Sound Events

Learning from data in the quaternion domain enables us to exploit intern...
12/19/2018

Discriminative analysis of the human cortex using spherical CNNs - a study on Alzheimer's disease diagnosis

In neuroimaging studies, the human cortex is commonly modeled as a spher...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.