Matches in SemOpenAlex for { <https://semopenalex.org/work/W3109899559> ?p ?o ?g. }
- W3109899559 abstract "Deep neural networks have been applied successfully to a wide variety of inverse problems arising in computational imaging. These networks are typically trained using a forward model that describes the measurement process to be inverted, which is often incorporated directly into the network itself. However, these approaches are sensitive to changes in the forward model: if at test time the forward model varies (even slightly) from the one the network was trained for, the reconstruction performance can degrade substantially. Given a network trained to solve an initial inverse problem with a known forward model, we propose two novel procedures that adapt the network to a change in the forward model, even without full knowledge of the change. Our approaches do not require access to more labeled data (i.e., ground truth images). We show these simple model adaptation approaches achieve empirical success in a variety of inverse problems, including deblurring, super-resolution, and undersampled image reconstruction in magnetic resonance imaging." @default.
- W3109899559 created "2020-12-07" @default.
- W3109899559 creator A5020368316 @default.
- W3109899559 creator A5031896965 @default.
- W3109899559 creator A5061121471 @default.
- W3109899559 date "2020-11-30" @default.
- W3109899559 modified "2023-09-27" @default.
- W3109899559 title "Model Adaptation for Inverse Problems in Imaging" @default.
- W3109899559 cites W1834627138 @default.
- W3109899559 cites W1901129140 @default.
- W3109899559 cites W2087332491 @default.
- W3109899559 cites W2103559027 @default.
- W3109899559 cites W2118103795 @default.
- W3109899559 cites W2155858138 @default.
- W3109899559 cites W2165698076 @default.
- W3109899559 cites W2173520492 @default.
- W3109899559 cites W2319561215 @default.
- W3109899559 cites W2395579298 @default.
- W3109899559 cites W2494719372 @default.
- W3109899559 cites W2552808051 @default.
- W3109899559 cites W2573726823 @default.
- W3109899559 cites W2595294663 @default.
- W3109899559 cites W2605195953 @default.
- W3109899559 cites W2763549966 @default.
- W3109899559 cites W2786808285 @default.
- W3109899559 cites W2804184144 @default.
- W3109899559 cites W2805167149 @default.
- W3109899559 cites W2805841154 @default.
- W3109899559 cites W2887280559 @default.
- W3109899559 cites W2911290743 @default.
- W3109899559 cites W2912027531 @default.
- W3109899559 cites W2952020389 @default.
- W3109899559 cites W2963226480 @default.
- W3109899559 cites W2963528163 @default.
- W3109899559 cites W2963917315 @default.
- W3109899559 cites W2964013315 @default.
- W3109899559 cites W2964186069 @default.
- W3109899559 cites W2964308363 @default.
- W3109899559 cites W2981551308 @default.
- W3109899559 cites W2995317998 @default.
- W3109899559 cites W2998280611 @default.
- W3109899559 cites W2998331447 @default.
- W3109899559 cites W3007318789 @default.
- W3109899559 cites W3008467700 @default.
- W3109899559 cites W3025242627 @default.
- W3109899559 cites W3031135805 @default.
- W3109899559 cites W3035219913 @default.
- W3109899559 cites W3082534285 @default.
- W3109899559 cites W3098020164 @default.
- W3109899559 cites W3100730608 @default.
- W3109899559 cites W3122711257 @default.
- W3109899559 hasPublicationYear "2020" @default.
- W3109899559 type Work @default.
- W3109899559 sameAs 3109899559 @default.
- W3109899559 citedByCount "0" @default.
- W3109899559 crossrefType "posted-content" @default.
- W3109899559 hasAuthorship W3109899559A5020368316 @default.
- W3109899559 hasAuthorship W3109899559A5031896965 @default.
- W3109899559 hasAuthorship W3109899559A5061121471 @default.
- W3109899559 hasConcept C106430172 @default.
- W3109899559 hasConcept C111472728 @default.
- W3109899559 hasConcept C11413529 @default.
- W3109899559 hasConcept C115961682 @default.
- W3109899559 hasConcept C119857082 @default.
- W3109899559 hasConcept C120665830 @default.
- W3109899559 hasConcept C121332964 @default.
- W3109899559 hasConcept C134306372 @default.
- W3109899559 hasConcept C135252773 @default.
- W3109899559 hasConcept C136197465 @default.
- W3109899559 hasConcept C138885662 @default.
- W3109899559 hasConcept C139807058 @default.
- W3109899559 hasConcept C154945302 @default.
- W3109899559 hasConcept C207467116 @default.
- W3109899559 hasConcept C2524010 @default.
- W3109899559 hasConcept C2777693668 @default.
- W3109899559 hasConcept C2780586882 @default.
- W3109899559 hasConcept C33923547 @default.
- W3109899559 hasConcept C41008148 @default.
- W3109899559 hasConcept C50644808 @default.
- W3109899559 hasConcept C9417928 @default.
- W3109899559 hasConceptScore W3109899559C106430172 @default.
- W3109899559 hasConceptScore W3109899559C111472728 @default.
- W3109899559 hasConceptScore W3109899559C11413529 @default.
- W3109899559 hasConceptScore W3109899559C115961682 @default.
- W3109899559 hasConceptScore W3109899559C119857082 @default.
- W3109899559 hasConceptScore W3109899559C120665830 @default.
- W3109899559 hasConceptScore W3109899559C121332964 @default.
- W3109899559 hasConceptScore W3109899559C134306372 @default.
- W3109899559 hasConceptScore W3109899559C135252773 @default.
- W3109899559 hasConceptScore W3109899559C136197465 @default.
- W3109899559 hasConceptScore W3109899559C138885662 @default.
- W3109899559 hasConceptScore W3109899559C139807058 @default.
- W3109899559 hasConceptScore W3109899559C154945302 @default.
- W3109899559 hasConceptScore W3109899559C207467116 @default.
- W3109899559 hasConceptScore W3109899559C2524010 @default.
- W3109899559 hasConceptScore W3109899559C2777693668 @default.
- W3109899559 hasConceptScore W3109899559C2780586882 @default.
- W3109899559 hasConceptScore W3109899559C33923547 @default.
- W3109899559 hasConceptScore W3109899559C41008148 @default.
- W3109899559 hasConceptScore W3109899559C50644808 @default.