Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Jul:107:570-604.

Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds

Michael Perlmutter  1 , Feng Gao  2 , Guy Wolf  3 , Matthew Hirn  4
Affiliations

Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds

Michael Perlmutter et al. Proc Mach Learn Res. 2020 Jul.

Abstract

The Euclidean scattering transform was introduced nearly a decade ago to improve the mathematical understanding of convolutional neural networks. Inspired by recent interest in geometric deep learning, which aims to generalize convolutional neural networks to manifold and graph-structured domains, we define a geometric scattering transform on manifolds. Similar to the Euclidean scattering transform, the geometric scattering transform is based on a cascade of wavelet filters and pointwise nonlinearities. It is invariant to local isometries and stable to certain types of diffeomorphisms. Empirical results demonstrate its utility on several geometric learning tasks. Our results generalize the deformation stability and local translation invariance of Euclidean scattering, and demonstrate the importance of linking the used filter structures to the underlying geometry of the data.

Keywords: geometric deep learning; spectral geometry; wavelet scattering.

PubMed Disclaimer

Figures

Figure 1:
Figure 1:
Geometric wavelets on the FAUST mesh with G(λ) = e−λ. From left to right j = −1,−3,−5,−7,−9. Positive values are colored red, while negative values are dark blue.
Figure 2:
Figure 2:
The geometric wavelet scattering transform SJL, illustrated for L = 2.
Figure 3:
Figure 3:
Spherical MNIST classificaion results.
See this image and copyright information in PMC

References

    1. Joakim Andén and Stéphane Mallat. Multiscale scattering for audio classification. In Proceedings of the ISMIR 2011 conference, pages 657–662, 2011.
    1. Joakim Andén and Stéphane Mallat. Deep scattering spectrum. IEEE Transactions on Signal Processing, 62(16):4114–4128, August 2014.
    1. Joakim Andén, Vincent Lostanlen, and Mallat Stéphane. Joint time-frequency scattering. IEEE Transactions on Signal Processing, 67(14):3704–3718, 2019.
    1. Pierre Bérard, Gérard Besson, and Gallot Sylvain. Embedding Riemannian manifolds by their heat kernel. Geometric and Functional Analysis, 4(4):373–398, 1994.
    1. Bogo Federica, Romero Javier, Loper Matthew, and Black Michael J.. FAUST: Dataset and evaluation for 3D mesh registration. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Piscataway, NJ, USA, 2014.

LinkOut - more resources