Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312452570> ?p ?o ?g. }
- W4312452570 abstract "Proximal methods have been extensively used to find maximum a posteriori (MAP) estimates of unknown images from degraded measurement. Recently, they have been mixed with neural networks (NN) to further improve the reconstruction quality. Two approaches can be distinguished: unfolded NNs, implementing a given iteration number of an optimisation algorithm, and plug-and-play (PnP) algorithms, incorporating NNs in existing optimisation algorithms. Unfolded NNs usually incorporate the measurement operator in the learning process, which can be prohibitive for applications with non-fixed measurement operators. PnP do not have this drawback, but involved NNs still depend on the underlying statistical models (e.g., higher noise level on the measurements requires stronger denoisers). In this work, we propose a PnP algorithm based on forward-backward (FB) iterations, where the learned denoiser is an unfolded NN based on dual-FB iterations. This NN is built to mimic a Gaussian denoiser from a MAP viewpoint. This allows us to introduce a regularisation parameter in the model to tune the regularization strength, similarly to standard variational approaches. This has the advantage of making the learned NN more adaptive to a variety of inverse problem statistical models, without requiring to train the NN for different noise levels." @default.
- W4312452570 created "2023-01-04" @default.
- W4312452570 creator A5041620227 @default.
- W4312452570 creator A5045608650 @default.
- W4312452570 creator A5062845079 @default.
- W4312452570 creator A5083254809 @default.
- W4312452570 date "2022-08-29" @default.
- W4312452570 modified "2023-10-15" @default.
- W4312452570 title "Dual Forward-Backward Unfolded Network for Flexible Plug-and-Play" @default.
- W4312452570 cites W1922442141 @default.
- W4312452570 cites W1946620893 @default.
- W4312452570 cites W1972440447 @default.
- W4312452570 cites W1998991750 @default.
- W4312452570 cites W2000594266 @default.
- W4312452570 cites W2006262045 @default.
- W4312452570 cites W2056370875 @default.
- W4312452570 cites W2087416986 @default.
- W4312452570 cites W2114423093 @default.
- W4312452570 cites W2118429861 @default.
- W4312452570 cites W2121927366 @default.
- W4312452570 cites W2982258910 @default.
- W4312452570 cites W2999778662 @default.
- W4312452570 cites W3101311698 @default.
- W4312452570 cites W3102025760 @default.
- W4312452570 cites W3103586216 @default.
- W4312452570 cites W3167568784 @default.
- W4312452570 cites W3194208020 @default.
- W4312452570 cites W3200625292 @default.
- W4312452570 doi "https://doi.org/10.23919/eusipco55093.2022.9909564" @default.
- W4312452570 hasPublicationYear "2022" @default.
- W4312452570 type Work @default.
- W4312452570 citedByCount "1" @default.
- W4312452570 countsByYear W43124525702022 @default.
- W4312452570 crossrefType "proceedings-article" @default.
- W4312452570 hasAuthorship W4312452570A5041620227 @default.
- W4312452570 hasAuthorship W4312452570A5045608650 @default.
- W4312452570 hasAuthorship W4312452570A5062845079 @default.
- W4312452570 hasAuthorship W4312452570A5083254809 @default.
- W4312452570 hasConcept C105795698 @default.
- W4312452570 hasConcept C111472728 @default.
- W4312452570 hasConcept C11413529 @default.
- W4312452570 hasConcept C115961682 @default.
- W4312452570 hasConcept C121332964 @default.
- W4312452570 hasConcept C124952713 @default.
- W4312452570 hasConcept C126255220 @default.
- W4312452570 hasConcept C134306372 @default.
- W4312452570 hasConcept C135252773 @default.
- W4312452570 hasConcept C138885662 @default.
- W4312452570 hasConcept C142362112 @default.
- W4312452570 hasConcept C154945302 @default.
- W4312452570 hasConcept C163294075 @default.
- W4312452570 hasConcept C163716315 @default.
- W4312452570 hasConcept C2776135515 @default.
- W4312452570 hasConcept C2780980858 @default.
- W4312452570 hasConcept C29265498 @default.
- W4312452570 hasConcept C33923547 @default.
- W4312452570 hasConcept C41008148 @default.
- W4312452570 hasConcept C49781872 @default.
- W4312452570 hasConcept C50644808 @default.
- W4312452570 hasConcept C62520636 @default.
- W4312452570 hasConcept C75553542 @default.
- W4312452570 hasConcept C9810830 @default.
- W4312452570 hasConcept C99498987 @default.
- W4312452570 hasConceptScore W4312452570C105795698 @default.
- W4312452570 hasConceptScore W4312452570C111472728 @default.
- W4312452570 hasConceptScore W4312452570C11413529 @default.
- W4312452570 hasConceptScore W4312452570C115961682 @default.
- W4312452570 hasConceptScore W4312452570C121332964 @default.
- W4312452570 hasConceptScore W4312452570C124952713 @default.
- W4312452570 hasConceptScore W4312452570C126255220 @default.
- W4312452570 hasConceptScore W4312452570C134306372 @default.
- W4312452570 hasConceptScore W4312452570C135252773 @default.
- W4312452570 hasConceptScore W4312452570C138885662 @default.
- W4312452570 hasConceptScore W4312452570C142362112 @default.
- W4312452570 hasConceptScore W4312452570C154945302 @default.
- W4312452570 hasConceptScore W4312452570C163294075 @default.
- W4312452570 hasConceptScore W4312452570C163716315 @default.
- W4312452570 hasConceptScore W4312452570C2776135515 @default.
- W4312452570 hasConceptScore W4312452570C2780980858 @default.
- W4312452570 hasConceptScore W4312452570C29265498 @default.
- W4312452570 hasConceptScore W4312452570C33923547 @default.
- W4312452570 hasConceptScore W4312452570C41008148 @default.
- W4312452570 hasConceptScore W4312452570C49781872 @default.
- W4312452570 hasConceptScore W4312452570C50644808 @default.
- W4312452570 hasConceptScore W4312452570C62520636 @default.
- W4312452570 hasConceptScore W4312452570C75553542 @default.
- W4312452570 hasConceptScore W4312452570C9810830 @default.
- W4312452570 hasConceptScore W4312452570C99498987 @default.
- W4312452570 hasLocation W43124525701 @default.
- W4312452570 hasOpenAccess W4312452570 @default.
- W4312452570 hasPrimaryLocation W43124525701 @default.
- W4312452570 hasRelatedWork W2023368175 @default.
- W4312452570 hasRelatedWork W2026741508 @default.
- W4312452570 hasRelatedWork W2065245038 @default.
- W4312452570 hasRelatedWork W2084622529 @default.
- W4312452570 hasRelatedWork W2761010937 @default.
- W4312452570 hasRelatedWork W2985456390 @default.
- W4312452570 hasRelatedWork W3181108989 @default.
- W4312452570 hasRelatedWork W38496366 @default.
- W4312452570 hasRelatedWork W4311526968 @default.