Kymatio: Scattering Transforms in Python

Mathieu Andreux, Tomás Angles, Georgios Exarchakis, Roberto Leonarduzzi, Gaspar Rochette +13 more
12/28/2018
cs.LGcs.CVcs.SD

Official code: kymatio/kymatio (857 stars, BSD-3-Clause, PyTorch, last commit 2026-06-09).

Abstract

The wavelet scattering transform is an invariant 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. All transforms may be executed on a GPU (in addition to CPU), offering a considerable speed up over CPU implementations. The package also has a small memory footprint, resulting inefficient memory usage. The source code, documentation, and examples are available undera BSD license at https://www.kymat.io/

View on arXivView PDF

Code Implementations(1)

kymatio/kymatioOfficial100%
PyTorchBSD-3-Clause

Wavelet scattering transforms in Python with GPU acceleration

857145Shell, PythonOct 2, 20184 months agoBSD-3-Clause
deep-learningkerasnumpypytorchscattering-transform+3 more

Similar Papers

Gabor frames and deep scattering networks in audio processing

78% match2017

Energy Propagation in Scattering Convolution Networks Can Be Arbitrarily Slow

76% match2024

WST-Graph: Topology-Preserving Wavelet Scattering Front-End for Speech Deepfake Detection

75% match2026

Explainable and Class-Revealing Signal Feature Extraction via Scattering Transform and Constrained Zeroth-Order Optimization

74% match2025

Scale Dependencies and Self-Similar Models with Wavelet Scattering Spectra

73% match1 repo462022

Scattering Spectra Models for Physics

73% match1 repo662023

Cite this paper

@article{andreux2018kymatio,
  title  = {Kymatio: Scattering Transforms in Python},
  author = {Mathieu Andreux and Tomás Angles and Georgios Exarchakis and Roberto Leonarduzzi and Gaspar Rochette and Louis Thiry and John Zarka and Stéphane Mallat and Joakim andén and Eugene Belilovsky and Joan Bruna and Vincent Lostanlen and Muawiz Chaudhary and Matthew J. Hirn and Edouard Oyallon and Sixin Zhang and Carmine Cella and Michael Eickenberg},
  year   = {2018},
  eprint = {1812.11214},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1812.11214}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1812.11214.svg)](https://codeofpaper.com/paper/1812.11214)

Discussion