FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203140881> ?p ?o ?g. }

• W3203140881 abstract "Purpose: This work aims at developing a generalizable MRI reconstruction model in the meta-learning framework. The standard benchmarks in meta-learning are challenged by learning on diverse task distributions. The proposed network learns the regularization function in a variational model and reconstructs MR images with various under-sampling ratios or patterns that may or may not be seen in the training data by leveraging a heterogeneous dataset. Methods: We propose an unrolling network induced by learnable optimization algorithms (LOA) for solving our nonconvex nonsmooth variational model for MRI reconstruction. In this model, the learnable regularization function contains a task-invariant common feature encoder and task-specific learner represented by a shallow network. To train the network we split the training data into two parts: training and validation, and introduce a bilevel optimization algorithm. The lower-level optimization trains task-invariant parameters for the feature encoder with fixed parameters of the task-specific learner on the training dataset, and the upper-level optimizes the parameters of the task-specific learner on the validation dataset. Results: The average PSNR increases significantly compared to the network trained through conventional supervised learning on the seen CS ratios. We test the result of quick adaption on the unseen tasks after meta-training and in the meanwhile saving half of the training time; Conclusion: We proposed a meta-learning framework consisting of the base network architecture, design of regularization, and bi-level optimization-based training. The network inherits the convergence property of the LOA and interpretation of the variational model. The generalization ability is improved by the designated regularization and bilevel optimization-based training algorithm." @default.
• W3203140881 created "2021-10-11" @default.
• W3203140881 creator A5000363449 @default.
• W3203140881 creator A5010278056 @default.
• W3203140881 creator A5058530714 @default.
• W3203140881 creator A5090335788 @default.
• W3203140881 date "2021-10-01" @default.
• W3203140881 modified "2023-09-27" @default.
• W3203140881 title "An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Dataset" @default.
• W3203140881 cites W1533861849 @default.
• W3203140881 cites W1542791059 @default.
• W3203140881 cites W1641498739 @default.
• W3203140881 cites W2133665775 @default.
• W3203140881 cites W2136334171 @default.
• W3203140881 cites W2194775991 @default.
• W3203140881 cites W2594014149 @default.
• W3203140881 cites W2601450892 @default.
• W3203140881 cites W2604388535 @default.
• W3203140881 cites W2604763608 @default.
• W3203140881 cites W2625674597 @default.
• W3203140881 cites W2742093937 @default.
• W3203140881 cites W2753160622 @default.
• W3203140881 cites W2784596339 @default.
• W3203140881 cites W2787501667 @default.
• W3203140881 cites W2795900505 @default.
• W3203140881 cites W2798559986 @default.
• W3203140881 cites W2889965839 @default.
• W3203140881 cites W2891244534 @default.
• W3203140881 cites W2902719825 @default.
• W3203140881 cites W2912528108 @default.
• W3203140881 cites W2946757877 @default.
• W3203140881 cites W2963043696 @default.
• W3203140881 cites W2963211188 @default.
• W3203140881 cites W2963303956 @default.
• W3203140881 cites W2963341924 @default.
• W3203140881 cites W2963580001 @default.
• W3203140881 cites W2963741406 @default.
• W3203140881 cites W2964078140 @default.
• W3203140881 cites W2964112702 @default.
• W3203140881 cites W2964121744 @default.
• W3203140881 cites W2964121937 @default.
• W3203140881 cites W2970105755 @default.
• W3203140881 cites W2979703761 @default.
• W3203140881 cites W2988803701 @default.
• W3203140881 cites W2994871715 @default.
• W3203140881 cites W2995253937 @default.
• W3203140881 cites W2998139906 @default.
• W3203140881 cites W3000314771 @default.
• W3203140881 cites W3001319253 @default.
• W3203140881 cites W3032377877 @default.
• W3203140881 cites W3044472408 @default.
• W3203140881 cites W3046934520 @default.
• W3203140881 cites W3091905774 @default.
• W3203140881 cites W3098900881 @default.
• W3203140881 cites W3100730608 @default.
• W3203140881 cites W3107389551 @default.
• W3203140881 cites W3154934604 @default.
• W3203140881 cites W3157428506 @default.
• W3203140881 cites W3163842339 @default.
• W3203140881 cites W3166523474 @default.
• W3203140881 cites W3179516356 @default.
• W3203140881 doi "https://doi.org/10.48550/arxiv.2110.00715" @default.
• W3203140881 hasPublicationYear "2021" @default.
• W3203140881 type Work @default.
• W3203140881 sameAs 3203140881 @default.
• W3203140881 citedByCount "0" @default.
• W3203140881 crossrefType "posted-content" @default.
• W3203140881 hasAuthorship W3203140881A5000363449 @default.
• W3203140881 hasAuthorship W3203140881A5010278056 @default.
• W3203140881 hasAuthorship W3203140881A5058530714 @default.
• W3203140881 hasAuthorship W3203140881A5090335788 @default.
• W3203140881 hasBestOaLocation W32031408811 @default.
• W3203140881 hasConcept C111919701 @default.
• W3203140881 hasConcept C11413529 @default.
• W3203140881 hasConcept C118505674 @default.
• W3203140881 hasConcept C119857082 @default.
• W3203140881 hasConcept C137836250 @default.
• W3203140881 hasConcept C153180895 @default.
• W3203140881 hasConcept C154945302 @default.
• W3203140881 hasConcept C193415008 @default.
• W3203140881 hasConcept C2776135515 @default.
• W3203140881 hasConcept C38652104 @default.
• W3203140881 hasConcept C41008148 @default.
• W3203140881 hasConceptScore W3203140881C111919701 @default.
• W3203140881 hasConceptScore W3203140881C11413529 @default.
• W3203140881 hasConceptScore W3203140881C118505674 @default.
• W3203140881 hasConceptScore W3203140881C119857082 @default.
• W3203140881 hasConceptScore W3203140881C137836250 @default.
• W3203140881 hasConceptScore W3203140881C153180895 @default.
• W3203140881 hasConceptScore W3203140881C154945302 @default.
• W3203140881 hasConceptScore W3203140881C193415008 @default.
• W3203140881 hasConceptScore W3203140881C2776135515 @default.
• W3203140881 hasConceptScore W3203140881C38652104 @default.
• W3203140881 hasConceptScore W3203140881C41008148 @default.
• W3203140881 hasLocation W32031408811 @default.
• W3203140881 hasOpenAccess W3203140881 @default.
• W3203140881 hasPrimaryLocation W32031408811 @default.
• W3203140881 hasRelatedWork W2356875448 @default.
• W3203140881 hasRelatedWork W2358489738 @default.
• W3203140881 hasRelatedWork W2385621972 @default.

• next