Abstract
Building nonexpansive Convolutional Neural Networks (CNNs) is a challenging problem that has recently gained a lot of attention from the image processing community. In particular, it appears to be the key to obtain convergent Plugand- Play algorithms. This problem, which relies on an accurate control of the the Lipschitz constant of the convolutional layers, has also been investigated for Generative Adversarial Networks to improve robustness to adversarial perturbations. However, to the best of our knowledge, no efficient method has been developed yet to build nonexpansive CNNs. In this paper, we develop an optimization algorithm that can be incorporated in the training of a network to ensure the nonexpansiveness of its convolutional layers. This is shown to allow us to build firmly nonexpansive CNNs. We apply the proposed approach to train a CNN for an image denoising task and show its effectiveness through simulations.
Original language | English |
---|---|
Title of host publication | ICASSP 2020 - IEEE International Conference on Acoustics, Speech and Signal Processing |
Publisher | IEEE |
Pages | 8658-8662 |
Number of pages | 5 |
ISBN (Electronic) | 9781509066315 |
DOIs | |
Publication status | Published - 14 May 2020 |
Event | 45th IEEE International Conference on Acoustics, Speech and Signal Processing 2020 - Barcelona, Spain Duration: 4 May 2020 → 8 May 2020 https://2020.ieeeicassp.org/ |
Publication series
Name | IEEE International Conference on Acoustics, Speech and Signal Processing |
---|---|
ISSN (Electronic) | 2379-190X |
Conference
Conference | 45th IEEE International Conference on Acoustics, Speech and Signal Processing 2020 |
---|---|
Abbreviated title | ICASSP 2020 |
Country/Territory | Spain |
City | Barcelona |
Period | 4/05/20 → 8/05/20 |
Internet address |
Keywords
- Image restoration
- Monotone operators
- Neural networks
- Nonexpansive operator
- Optimization
ASJC Scopus subject areas
- Software
- Signal Processing
- Electrical and Electronic Engineering