Skip to Main content Skip to Navigation
Conference papers

Wavelets in the Deep Learning ERA

Abstract : Sparsity based methods, such as wavelets, have been state-of-the-art for more than 20 years for inverse problems before being overtaken by neural networks. In particular, U-nets have proven to be extremely effective. Their main ingredients are a highly non-linear processing, a massive learning made possible by the flourishing of optimization algorithms with the power of computers (GPU) and the use of large available data sets for training. While the many stages of non-linearity are intrinsic to deep learning, the usage of learning with training data could also be exploited by sparsity based approaches. The aim of our study is to push the limits of sparsity with learning, and comparing the results with U-nets. We present a new network architecture, which conserves the properties of sparsity based methods such as exact reconstruction and good generalization properties, while fostering the power of neural networks for learning and fast calculation. We evaluate the model on image denoising tasks and show it is competitive with learning-based models.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03020214
Contributor : Zaccharie Ramzi Connect in order to contact the contributor
Submitted on : Monday, November 23, 2020 - 5:39:41 PM
Last modification on : Tuesday, October 19, 2021 - 7:01:52 PM
Long-term archiving on: : Thursday, February 25, 2021 - 1:37:42 PM

File

learnlets_eusipco_2020 (6).pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03020214, version 1

Citation

Zaccharie Ramzi, Jean-Luc Starck, Thomas Moreau, Philippe Ciuciu. Wavelets in the Deep Learning ERA. EUSIPCO 2020 - 28th European Signal Processing Conference, Jan 2021, Amsterdam, Netherlands. ⟨hal-03020214⟩

Share

Metrics

Record views

303

Files downloads

820