Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Learning Lipschitz-Controlled Activation Functions in Neural Networks for Plug-and-Play Image Reconstruction Methods
 
conference paper not in proceedings

Learning Lipschitz-Controlled Activation Functions in Neural Networks for Plug-and-Play Image Reconstruction Methods

Bohra, Pakshal Narendra  
•
Perdios, Dimitris  
•
Goujon, Alexis  
Show more
December 13, 2021
NeurIPS 2021 Workshop on Deep Learning and Inverse Problems

Ill-posed linear inverse problems are frequently encountered in image reconstruction tasks. Image reconstruction methods that combine the Plug-and-Play (PnP) priors framework with convolutional neural network (CNN) based denoisers have shown impressive performances. However, it is non-trivial to guarantee the convergence of such algorithms, which is necessary for sensitive applications such as medical imaging. It has been shown that PnP algorithms converge when deployed with a certain class of averaged denoising operators. While such averaged operators can be built from 1-Lipschitz CNNs, imposing such a constraint on CNNs usually leads to a severe drop in performance. To mitigate this effect, we propose the use of deep spline neural networks which benefit from learnable piecewise-linear spline activation functions. We introduce "slope normalization" to control the Lipschitz constant of these activation functions. We show that averaged denoising operators built from 1-Lipschitz deep spline networks consistently outperform those built from 1-Lipschitz ReLU networks.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

bohra2101.pdf

Type

Publisher

Version

http://purl.org/coar/version/c_970fb48d4fbd8a85

Access type

openaccess

License Condition

CC BY-NC-ND

Size

7.17 MB

Format

Adobe PDF

Checksum (MD5)

ea21c6c1d5ff7b996145103800bae14d

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés