2020

DeepSphere: a graph-based spherical CNN

Defferrard, Michaël, Milani, Martino, Gusset, Frédérick et al.

Understand

Designing a convolution for a spherical neural network requires a delicate tradeoff between efficiency and rotation equivariance.

DeepSphere, a method based on a graph representation of the sampled sphere, strikes a controllable balance between these two desiderata.
This contribution is twofold.
First, we study both theoretically and empirically how equivariance is affected by the underlying graph with respect to the number of vertices and neighbors.

Built on

Spherical cnns on unstructured grids
Original
Chiyu ”Max” Jiang, Jingwei Huang, Karthik Kashinath, Prabhat, Philip Marcus, and Matthias Niessner · 1901
Earlier work this paper cites.
Gauge equivariant convolutional networks and the icosahedral cnn
Original
Taco S. Cohen, Maurice Weiler, Berkay Kicanaoglu, and Max Welling · 1902
Earlier work this paper cites.
Deepsphere: towards an equivariant graph-based spherical cnn
Original
Michaël Defferrard, Nathanaël Perraudin, Tomasz Kacprzak, and Raphael Sgier · 1904
Earlier work this paper cites.
Icosahedral discretization of the two-sphere
John R Baumgardner and Paul O Frederickson · 1985
Earlier work this paper cites.
Computing fourier transforms and convolutions on the 2-sphere
J. R. Driscoll and D. M. Healy · 1994
Earlier work this paper cites.
The healpix primer
Krzysztof M Gorski, Benjamin D Wandelt, Frode K Hansen, Eric Hivon, and Anthony J Banday · 1999
Earlier work this paper cites.
Healpix: a framework for high-resolution discretization and fast analysis of data distributed on the sphere
Krzysztof M Gorski, Eric Hivon, AJ Banday, Benjamin D Wandelt, Frode K Hansen, Mstvos Reinecke, and Matthia Bartelmann · 2005
Earlier work this paper cites.
Convergence of laplacian eigenmaps
Mikhail Belkin and Partha Niyogi · 2007
Earlier work this paper cites.
Matplotlib: A 2d graphics environment
J. D. Hunter · 2007
Earlier work this paper cites.
Towards a theoretical foundation for laplacian-based manifold methods
Mikhail Belkin and Partha Niyogi · 2008
Earlier work this paper cites.

Similar

Gravitational lensing
M. Bartelmann · 2010
Cited alongside, same era.
The numpy array: a structure for efficient numerical computation
Stéfan van der Walt, S Chris Colbert, and Gael Varoquaux · 2011
Cited alongside, same era.
Spectral networks and locally connected networks on graphs
Original
Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun · 2013
Cited alongside, same era.
TensorFlow: Large-scale machine learning on heterogeneous systems, 2015
Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Jozefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenberg, Dandelion Mané, Rajat Monga, Sherry Moore, Derek Murray, Chris Olah, Mike Schuster, Jonathon Shlens, Benoit Steiner, Ilya Sutskever, Kunal Talwar, Paul Tucker, Vincent Vanhoucke, Vijay Vasudevan, Fernanda Viégas, Oriol Vinyals, Pete Warden, Martin Wattenberg, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng · 2015
Cited alongside, same era.
Shapenet: An information-rich 3d model repository
Original
Angel X Chang, Thomas Funkhouser, Leonidas Guibas, Pat Hanrahan, Qixing Huang, Zimo Li, Silvio Savarese, Manolis Savva, Shuran Song, Hao Su, et al · 2015
Cited alongside, same era.
Learning shape correspondence with anisotropic convolutional neural networks
Davide Boscaini, Jonathan Masci, Emanuele Rodolà, and Michael Bronstein · 2016
Cited alongside, same era.
Convolutional neural networks on graphs with fast localized spectral filtering
Original
Michaël Defferrard, Xavier Bresson, and Pierre Vandergheynst · 2016
Cited alongside, same era.
Planck 2015 results. i. overview of products and scientific results
Planck Collaboration · 2016
Cited alongside, same era.
Spherical convolutions and their application in molecular modelling
Wouter Boomsma and Jes Frellsen · 2017
Cited alongside, same era.
Graph-based classification of omnidirectional images
Original
Renata Khasanova and Pascal Frossard · 2017
Cited alongside, same era.
Pygsp: Graph signal processing in python
Michaël Defferrard, Lionel Martin, Rodrigo Pena, and Nathanaël Perraudin
Cited in the paper.

Then

Segmenting and tracking extreme climate events using neural networks
Mayur Mudigonda, Sookyung Kim, Ankur Mahesh, Samira Kahou, Karthik Kashinath, Dean Williams, Vincen Michalski, Travis O’Brien, and Mr Prabhat · 2017
Later among the works it cites.
Large-scale 3d shape retrieval from shapenet core55: Shrec’17 track
Manolis Savva, Fisher Yu, Hao Su, Asako Kanezaki, Takahiko Furuya, Ryutarou Ohbuchi, Zhichao Zhou, Rui Yu, Song Bai, Xiang Bai, et al · 2017
Later among the works it cites.
Cosmological model discrimination with deep learning
Original
J. Schmelzle, A. Lucchi, T. Kacprzak, A. Amara, R. Sgier, A. Réfrégier, and T. Hofmann · 2017
Later among the works it cites.
Learning spherical convolution for fast features from 360 imagery
Yu-Chuan Su and Kristen Grauman · 2017
Later among the works it cites.
Spherical cnns
Original
Taco S Cohen, Mario Geiger, Jonas Koehler, and Max Welling · 2018
Later among the works it cites.
Spherenet: Learning spherical representations for detection and classification in omnidirectional images
Benjamin Coors, Alexandru Paul Condurache, and Andreas Geiger · 2018
Later among the works it cites.
Learning so(3) equivariant representations with spherical cnns
Original
Carlos Esteves, Christine Allen-Blanchette, Ameesh Makadia, and Kostas Daniilidis · 2018
Later among the works it cites.
Deepsphere: Efficient spherical convolutional neural network with healpix sampling for cosmological applications
Original
Nathanaël Perraudin, Michaël Defferrard, Tomasz Kacprzak, and Raphael Sgier · 2019
Later among the works it cites.
healpy: equal area pixelization and spherical harmonics transforms for data on the sphere in python
Original
Andrea Zonca, Leo Singer, Daniel Lenz, Martin Reinecke, Cyrille Rosset, Eric Hivon, and Krzysztof Gorski · 2019
Later among the works it cites.
SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python
Pauli Virtanen, Ralf Gommers, Travis E. Oliphant, Matt Haberland, Tyler Reddy, David Cournapeau, Evgeni Burovski, Pearu Peterson, Warren Weckesser, Jonathan Bright, Stéfan J. van der Walt, Matthew Brett, Joshua Wilson, K. Jarrod Millman, Nikolay Mayorov, Andrew R. J. Nelson, Eric Jones, Robert Kern, Eric Larson, CJ Carey, İlhan Polat, Yu Feng, Eric W. Moore, Jake Vand erPlas, Denis Laxalde, Josef Perktold, Robert Cimrman, Ian Henriksen, E. A. Quintero, Charles R Harris, Anne M. Archibald, Antônio H. Ribeiro, Fabian Pedregosa, Paul van Mulbregt, and SciPy 1. 0 Contributors · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…