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. |
Year | Venue | Keywords |
---|---|---|
2020 | JOURNAL OF MACHINE LEARNING RESEARCH | Scattering Transform,GPUs,Wavelets,Convolutional Networks,Invariance |
DocType | Volume | Issue |
Journal | 21 | 60 |
ISSN | Citations | PageRank |
1532-4435 | 0 | 0.34 |
References | Authors | |
0 | 18 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mathieu Andreux | 1 | 0 | 0.34 |
Tomás Angles | 2 | 4 | 1.43 |
Georgios Exarchakis | 3 | 0 | 0.34 |
Roberto F. Leonarduzzi | 4 | 12 | 4.17 |
Gaspar Rochette | 5 | 0 | 0.68 |
Louis Thiry | 6 | 3 | 2.42 |
John Zarka | 7 | 0 | 1.01 |
Stéphane Mallat | 8 | 4107 | 718.30 |
Joakim Andén | 9 | 64 | 7.70 |
Eugene Belilovsky | 10 | 23 | 6.88 |
J. Bruna | 11 | 1697 | 82.95 |
vincent lostanlen | 12 | 27 | 8.88 |
Muawiz Chaudhary | 13 | 0 | 0.34 |
Matthew J. Hirn | 14 | 33 | 6.48 |
Edouard Oyallon | 15 | 17 | 3.64 |
Sixin Zhang | 16 | 0 | 0.34 |
Carmine-Emanuele Cella | 17 | 0 | 0.34 |
Michael Eickenberg | 18 | 0 | 1.01 |