English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Bilevel learning is a powerful optimization technique that has extensivelybeen employed in recent years to bridge the world of model-driven variationalapproaches with data-driven methods. Upon suitable parametrization of thedesired quantities of interest (e.g., regularization terms or discretizationfilters), such approach computes optimal parameter values by solving a nestedoptimization problem where the variational model acts as a constraint. In thiswork, we consider two different use cases of bilevel learning for the problemof image restoration. First, we focus on learning scalar weights andconvolutional filters defining a Field of Experts regularizer to restorenatural images degraded by blur and noise. For improving the practicalperformance, the lower-level problem is solved by means of a gradient descentscheme combined with a line-search strategy based on the Barzilai-Borwein rule.As a second application, the bilevel setup is employed for learning adiscretization of the popular total variation regularizer for solving imagerestoration problems (in particular, deblurring and super-resolution).Numerical results show the effectiveness of the approach and theirgeneralization to multiple tasks.

Bilevel learning of regularization models and their discretization for image deblurring and super-resolution