Skip to content
conftrace_
2020 JMLR JMLR 2020

Kymatio: Scattering Transforms in Python

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 and GPUs, the latter offering a significant speedup over the former. The package also has a small memory footprint. Source code, documentation, and examples are available under a BSD license at https://www.kymat.io. [abs] [ pdf ][ bib ] [ code ] © JMLR 2020. (edit, beta)

Authors

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

Topics

Machine Learning > Core Methods > Representation Learning Deep Learning > Architectures > Neural Networks

Keywords

signal processing invariant representation wavelet scattering transform
Download PDF

More from JMLR 2020

All JMLR 2020 papers →
Self-paced Multi-view Co-training
Robust Asynchronous Stochastic Gradient-Push: Asymptotically Optimal and Network-Independent Performance for Strongly Convex Functions
Exact Guarantees on the Absence of Spurious Local Minima for Non-negative Rank-1 Robust Principal Component Analysis
Multiparameter Persistence Landscapes
Generalized Optimal Matching Methods for Causal Inference
Unique Sharp Local Minimum in L1-minimization Complete Dictionary Learning