DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications

10/29/2018
by   Nathanaël Perraudin, et al.
0

Convolutional Neural Networks (CNNs) are a cornerstone of the Deep Learning toolbox and have led to many breakthroughs in Artificial Intelligence. These networks have mostly been developed for regular Euclidean domains such as those supporting images, audio, or video. Because of their success, CNN-based methods are becoming increasingly popular in Cosmology. Cosmological data often comes as spherical maps, which make the use of the traditional CNNs more complicated. The commonly used pixelization scheme for spherical maps is the Hierarchical Equal Area isoLatitude Pixelisation (HEALPix). We present a spherical CNN for analysis of full and partial HEALPix maps, which we call DeepSphere. The spherical CNN is constructed by representing the sphere as a graph. Graphs are versatile data structures that can act as a discrete representation of a continuous manifold. Using the graph-based representation, we define many of the standard CNN operations, such as convolution and pooling. With filters restricted to being radial, our convolutions are equivariant to rotation on the sphere, and DeepSphere can be made invariant or equivariant to rotation. This way, DeepSphere is a special case of a graph CNN, tailored to the HEALPix sampling of the sphere. This approach is computationally more efficient than using spherical harmonics to perform convolutions. We demonstrate the method on a classification problem of weak lensing mass maps from two cosmological models and compare the performance of the CNN with that of two baseline classifiers. The results show that the performance of DeepSphere is always superior or equal to both of these baselines. For high noise levels and for data covering only a smaller fraction of the sphere, DeepSphere achieves typically 10 classification accuracy than those baselines. Finally, we show how learned filters can be visualized to introspect the neural network.

READ FULL TEXT

page 3

page 12

research
04/08/2019

DeepSphere: towards an equivariant graph-based spherical CNN

Spherical data is found in many applications. By modeling the discretize...
research
07/19/2021

OSLO: On-the-Sphere Learning for Omnidirectional images and its application to 360-degree image compression

State-of-the-art 2D image compression schemes rely on the power of convo...
research
09/27/2022

Scalable and Equivariant Spherical CNNs by Discrete-Continuous (DISCO) Convolutions

No existing spherical convolutional neural network (CNN) framework is bo...
research
11/20/2018

SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree Images

Omni-directional cameras have many advantages over conventional cameras ...
research
07/30/2019

Orientation-aware Semantic Segmentation on Icosahedron Spheres

We address semantic segmentation on omnidirectional images, to leverage ...
research
12/08/2020

Rotation-Invariant Autoencoders for Signals on Spheres

Omnidirectional images and spherical representations of 3D shapes cannot...
research
12/30/2020

DeepSphere: a graph-based spherical CNN

Designing a convolution for a spherical neural network requires a delica...

Please sign up or login with your details

Forgot password? Click here to reset