Kymatio: Scattering transforms in python

2018

Abstract

The wavelet scattering transform is an invariant and stable signal representation suitable for many signal processing and machine learning applications. We present the Kymatio software package, an easy-to-use, high-performance Python implementation of the scattering transform in 1D, 2D, and 3D that is compatible with modern deep learning frameworks, including PyTorch and TensorFlow/Keras. The transforms are implemented on both CPUs c 2020 Mathieu Andreux, Tomás Angles, Georgios Exarchakis, Roberto Leonarduzzi, Gaspar Rochette, Louis Thiry, John Zarka, Stéphane Mallat, Joakim Andén, Eugene Belilovsky, Joan Bruna, Vincent Lostanlen, Muawiz Chaudhary, Matthew J. Hirn, Edouard Oyallon, Sixin Zhang, Carmine Cella, Michael Eickenberg.

Authors

Mathieu Andreux
Tomás Angles
Georgios Exarchakis
Roberto Leonarduzzi
Gaspar Rochette
Louis Thiry
John Zarka
Stéphane Mallat
Joakim Andén
Eugene Belilovsky
Joan Bruna
Vincent Lostanlen
Muawiz Chaudhary
Matthew Hirn
Edouard Oyallon
Sixin Zhang
Carmine Emanuele Cella
Michael Eickenberg