DeepSphere: towards an equivariant graph-based spherical CNN

Spherical data is found in many applications. By modeling the discretized sphere as a graph, we can accommodate non-uniformly distributed, partial, and changing samplings. Moreover, graph convolutions are computationally more efficient than spherical convolutions. As equivariance is desired to exploit rotational symmetries, we discuss how to approach rotation equivariance using the graph neural network introduced in Defferrard et al. (2016). Experiments show good performance on rotation-invariant learning problems. Code and examples are available at this https URL

[1]  Pierre Vandergheynst,et al.  Stationary Signal Processing on Graphs , 2016, IEEE Transactions on Signal Processing.

[2]  Pascal Frossard,et al.  The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains , 2012, IEEE Signal Processing Magazine.

[3]  Nizhnij Arkhyz,et al.  Gauss-Legendre Sky Pixelization (GLESP) for CMB maps , 2008 .

[4]  Matthias Nießner,et al.  Spherical CNNs on Unstructured Grids , 2019, ICLR.

[5]  Andreas Geiger,et al.  SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images , 2018, ECCV.

[6]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[7]  Kostas Daniilidis,et al.  3D object classification and retrieval with Spherical CNNs , 2017, ArXiv.

[8]  K. Gorski,et al.  HEALPix: A Framework for High-Resolution Discretization and Fast Analysis of Data Distributed on the Sphere , 2004, astro-ph/0409513.

[9]  Max Welling,et al.  Spherical CNNs , 2018, ICLR.

[10]  Gene H. Golub,et al.  Optimal Surface Smoothing as Filter Design , 1996, ECCV.

[11]  A. Makadia,et al.  Learning SO(3) Equivariant Representations with Spherical CNNs , 2019, International Journal of Computer Vision.

[12]  Adam Amara,et al.  Fast generation of covariance matrices for weak lensing , 2018, Journal of Cosmology and Astroparticle Physics.

[13]  Nathanael Perraudin,et al.  DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications , 2018, Astron. Comput..

[14]  Max Welling,et al.  Group Equivariant Convolutional Networks , 2016, ICML.

[15]  M. Tomasi,et al.  Convolutional neural networks on the HEALPix sphere: a pixel-based algorithm and its application to CMB data analysis , 2019, Astronomy & Astrophysics.

[16]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.

[17]  Kenneth Patton,et al.  Cosmological constraints from the convergence 1-point probability distribution , 2016, Monthly Notices of the Royal Astronomical Society.

[18]  Pierre Vandergheynst,et al.  Wavelets on Graphs via Spectral Graph Theory , 2009, ArXiv.

[19]  Risi Kondor,et al.  On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups , 2018, ICML.

[20]  Pascal Frossard,et al.  Graph-Based Classification of Omnidirectional Images , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[21]  Gilbert Strang,et al.  The Discrete Cosine Transform , 1999, SIAM Rev..

[22]  Kristen Grauman,et al.  Flat2Sphere: Learning Spherical Convolution for Fast Features from 360° Imagery , 2017, NIPS 2017.