WaveTF: a fast 2D wavelet transform for machine learning in Keras

The wavelet transform is a powerful tool for performing multiscale analysis and it is a key subroutine in countless applications, from image processing to astronomy. Recently, it has extended its range of users to include the ever growing machine learning community. For a wavelet library to be efficiently adopted in this context, it needs to provide transformations which can be integrated seamlessly in already existing machine learning workflows and neural networks, being able to leverage the same libraries and run on the same hardware (e.g., CPU vs GPU) as the rest of the machine learning pipeline, without impacting training and evaluation performance. In this paper we present WaveTF, a wavelet library available as a Keras layer, which leverages TensorFlow to exploit GPU parallelism and can be used to enrich already existing machine learning workflows. To demonstrate its efficiency we compare its raw performance against other alternative libraries and finally measure the overhead it causes to the learning process when it is integrated in an already existing Convolutional Neural Network.

@InProceedings{Ver21,
  author       = {Versaci, F.},
  title        = {WaveTF: a fast 2D wavelet transform for machine learning in Keras},
  booktitle    = {Pattern Recognition. ICPR International Workshops and Challenges. CADL@ICPR 2021},
  series       = {Lecture Notes in Computer Science},
  volume       = {12661},
  pages        = {605-618},
  month        = {january},
  year         = {2021},
  publisher    = {Springer},
  keywords     = {Discrete wavelet transforms, Machine learning, Neural networks},
  doi          = {10.1007/978-3-030-68763-2_46},
  isbn         = {978-3-030-68763-2},
  url          = {https://publications.crs4.it/pubdocs/2021/Ver21},
}