Matches in SemOpenAlex for { <https://semopenalex.org/work/W2578009003> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2578009003 abstract "The promise of compressive sensing (CS) has been offset by two significant challenges. First, real-world data is not exactly sparse in a fixed basis. Second, current high-performance recovery algorithms are slow to converge, which limits CS to either non-real-time applications or scenarios where massive back-end computing is available. In this paper, we attack both of these challenges head-on by developing a new signal recovery framework we call DeepInverse that learns the inverse transformation from measurement vectors to signals using a deep convolutional network. When trained on a set of representative images, the network learns both a representation for the signals (addressing challenge one) and an inverse map approximating a greedy or convex recovery algorithm (addressing challenge two). Our experiments indicate that the DeepInverse network closely approximates the solution produced by state-of-the-art CS recovery algorithms yet is hundreds of times faster in run time. The tradeoff for the ultrafast run time is a computationally intensive, off-line training procedure typical to deep networks. However, the training needs to be completed only once, which makes the approach attractive for a host of sparse recovery problems." @default.
- W2578009003 created "2017-01-26" @default.
- W2578009003 creator A5018348533 @default.
- W2578009003 creator A5072713767 @default.
- W2578009003 date "2017-03-01" @default.
- W2578009003 modified "2023-10-16" @default.
- W2578009003 title "Learning to invert: Signal recovery via Deep Convolutional Networks" @default.
- W2578009003 cites W1500801837 @default.
- W2578009003 cites W2082029531 @default.
- W2578009003 cites W2104266187 @default.
- W2578009003 cites W2129638195 @default.
- W2578009003 cites W2145096794 @default.
- W2578009003 cites W2160547390 @default.
- W2578009003 cites W2273561594 @default.
- W2578009003 cites W2289917018 @default.
- W2578009003 cites W2963676935 @default.
- W2578009003 cites W3102722370 @default.
- W2578009003 cites W4250955649 @default.
- W2578009003 doi "https://doi.org/10.1109/icassp.2017.7952561" @default.
- W2578009003 hasPublicationYear "2017" @default.
- W2578009003 type Work @default.
- W2578009003 sameAs 2578009003 @default.
- W2578009003 citedByCount "195" @default.
- W2578009003 countsByYear W25780090032017 @default.
- W2578009003 countsByYear W25780090032018 @default.
- W2578009003 countsByYear W25780090032019 @default.
- W2578009003 countsByYear W25780090032020 @default.
- W2578009003 countsByYear W25780090032021 @default.
- W2578009003 countsByYear W25780090032022 @default.
- W2578009003 countsByYear W25780090032023 @default.
- W2578009003 crossrefType "proceedings-article" @default.
- W2578009003 hasAuthorship W2578009003A5018348533 @default.
- W2578009003 hasAuthorship W2578009003A5072713767 @default.
- W2578009003 hasBestOaLocation W25780090032 @default.
- W2578009003 hasConcept C108583219 @default.
- W2578009003 hasConcept C11413529 @default.
- W2578009003 hasConcept C124066611 @default.
- W2578009003 hasConcept C124851039 @default.
- W2578009003 hasConcept C154945302 @default.
- W2578009003 hasConcept C175291020 @default.
- W2578009003 hasConcept C177264268 @default.
- W2578009003 hasConcept C199360897 @default.
- W2578009003 hasConcept C2989281035 @default.
- W2578009003 hasConcept C41008148 @default.
- W2578009003 hasConcept C51823790 @default.
- W2578009003 hasConcept C81363708 @default.
- W2578009003 hasConceptScore W2578009003C108583219 @default.
- W2578009003 hasConceptScore W2578009003C11413529 @default.
- W2578009003 hasConceptScore W2578009003C124066611 @default.
- W2578009003 hasConceptScore W2578009003C124851039 @default.
- W2578009003 hasConceptScore W2578009003C154945302 @default.
- W2578009003 hasConceptScore W2578009003C175291020 @default.
- W2578009003 hasConceptScore W2578009003C177264268 @default.
- W2578009003 hasConceptScore W2578009003C199360897 @default.
- W2578009003 hasConceptScore W2578009003C2989281035 @default.
- W2578009003 hasConceptScore W2578009003C41008148 @default.
- W2578009003 hasConceptScore W2578009003C51823790 @default.
- W2578009003 hasConceptScore W2578009003C81363708 @default.
- W2578009003 hasLocation W25780090031 @default.
- W2578009003 hasLocation W25780090032 @default.
- W2578009003 hasOpenAccess W2578009003 @default.
- W2578009003 hasPrimaryLocation W25780090031 @default.
- W2578009003 hasRelatedWork W1584396216 @default.
- W2578009003 hasRelatedWork W2051659189 @default.
- W2578009003 hasRelatedWork W2082153276 @default.
- W2578009003 hasRelatedWork W2092550984 @default.
- W2578009003 hasRelatedWork W2134502174 @default.
- W2578009003 hasRelatedWork W2571836903 @default.
- W2578009003 hasRelatedWork W2584735684 @default.
- W2578009003 hasRelatedWork W2944491429 @default.
- W2578009003 hasRelatedWork W2950921922 @default.
- W2578009003 hasRelatedWork W2999294160 @default.
- W2578009003 isParatext "false" @default.
- W2578009003 isRetracted "false" @default.
- W2578009003 magId "2578009003" @default.
- W2578009003 workType "article" @default.