FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3170881570> ?p ?o ?g. }

• W3170881570 endingPage "7126" @default.
• W3170881570 startingPage "7112" @default.
• W3170881570 abstract "Deep learning has recently been intensively studied in the context of image compressive sensing (CS) to discover and represent complicated image structures. These approaches, however, either suffer from nonflexibility for an arbitrary sampling ratio or lack an explicit deep-learned regularization term. This paper aims to solve the CS reconstruction problem by combining the deep-learned regularization term and proximal operator. We first introduce a regularization term using a carefully designed residual-regressive net, which can measure the distance between a corrupted image and a clean image set and accurately identify to which subspace the corrupted image belongs. We then address a proximal operator with a tailored dilated residual channel attention net, which enables the learned proximal operator to map the distorted image into the clean image set. We adopt an adaptive proximal selection strategy to embed the network into the loop of the CS image reconstruction algorithm. Moreover, a self-ensemble strategy is presented to improve CS recovery performance. We further utilize state evolution to analyze the effectiveness of the designed networks. Extensive experiments also demonstrate that our method can yield superior accurate reconstruction (PSNR gain over 1 dB) compared to other competing approaches while achieving the current state-of-the-art image CS reconstruction performance. The test code is available at https://github.com/zjut-gwl/CSDRCANet." @default.
• W3170881570 created "2021-06-22" @default.
• W3170881570 creator A5013436511 @default.
• W3170881570 creator A5015090426 @default.
• W3170881570 creator A5015224523 @default.
• W3170881570 creator A5064422527 @default.
• W3170881570 creator A5082634513 @default.
• W3170881570 creator A5089487881 @default.
• W3170881570 creator A5091103434 @default.
• W3170881570 date "2021-01-01" @default.
• W3170881570 modified "2023-10-18" @default.
• W3170881570 title "Deep-Learned Regularization and Proximal Operator for Image Compressive Sensing" @default.
• W3170881570 cites W1502532067 @default.
• W3170881570 cites W2018990310 @default.
• W3170881570 cites W2030369007 @default.
• W3170881570 cites W2038085946 @default.
• W3170881570 cites W2082029531 @default.
• W3170881570 cites W2087416986 @default.
• W3170881570 cites W2103375347 @default.
• W3170881570 cites W2108598243 @default.
• W3170881570 cites W2122548617 @default.
• W3170881570 cites W2145096794 @default.
• W3170881570 cites W2145568341 @default.
• W3170881570 cites W2159563318 @default.
• W3170881570 cites W2263468737 @default.
• W3170881570 cites W2556068545 @default.
• W3170881570 cites W2604885021 @default.
• W3170881570 cites W2613155248 @default.
• W3170881570 cites W2741137940 @default.
• W3170881570 cites W2769849425 @default.
• W3170881570 cites W2798559986 @default.
• W3170881570 cites W2902719825 @default.
• W3170881570 cites W2911973879 @default.
• W3170881570 cites W2914390600 @default.
• W3170881570 cites W2963081547 @default.
• W3170881570 cites W2963206527 @default.
• W3170881570 cites W2963676935 @default.
• W3170881570 cites W2980149757 @default.
• W3170881570 cites W2982505009 @default.
• W3170881570 cites W3009991223 @default.
• W3170881570 cites W3035446378 @default.
• W3170881570 cites W3081108418 @default.
• W3170881570 cites W3084306245 @default.
• W3170881570 cites W3090249111 @default.
• W3170881570 cites W3098848552 @default.
• W3170881570 cites W3098900881 @default.
• W3170881570 cites W3102025760 @default.
• W3170881570 cites W3115447952 @default.
• W3170881570 cites W3134510327 @default.
• W3170881570 cites W4242059867 @default.
• W3170881570 cites W4250955649 @default.
• W3170881570 doi "https://doi.org/10.1109/tip.2021.3088611" @default.
• W3170881570 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34138708" @default.
• W3170881570 hasPublicationYear "2021" @default.
• W3170881570 type Work @default.
• W3170881570 sameAs 3170881570 @default.
• W3170881570 citedByCount "19" @default.
• W3170881570 countsByYear W31708815702021 @default.
• W3170881570 countsByYear W31708815702022 @default.
• W3170881570 countsByYear W31708815702023 @default.
• W3170881570 crossrefType "journal-article" @default.
• W3170881570 hasAuthorship W3170881570A5013436511 @default.
• W3170881570 hasAuthorship W3170881570A5015090426 @default.
• W3170881570 hasAuthorship W3170881570A5015224523 @default.
• W3170881570 hasAuthorship W3170881570A5064422527 @default.
• W3170881570 hasAuthorship W3170881570A5082634513 @default.
• W3170881570 hasAuthorship W3170881570A5089487881 @default.
• W3170881570 hasAuthorship W3170881570A5091103434 @default.
• W3170881570 hasBestOaLocation W31708815702 @default.
• W3170881570 hasConcept C104317684 @default.
• W3170881570 hasConcept C106430172 @default.
• W3170881570 hasConcept C108583219 @default.
• W3170881570 hasConcept C11413529 @default.
• W3170881570 hasConcept C115961682 @default.
• W3170881570 hasConcept C124851039 @default.
• W3170881570 hasConcept C141379421 @default.
• W3170881570 hasConcept C153180895 @default.
• W3170881570 hasConcept C154945302 @default.
• W3170881570 hasConcept C155512373 @default.
• W3170881570 hasConcept C158448853 @default.
• W3170881570 hasConcept C17020691 @default.
• W3170881570 hasConcept C185592680 @default.
• W3170881570 hasConcept C2776135515 @default.
• W3170881570 hasConcept C31972630 @default.
• W3170881570 hasConcept C32834561 @default.
• W3170881570 hasConcept C41008148 @default.
• W3170881570 hasConcept C55493867 @default.
• W3170881570 hasConcept C86339819 @default.
• W3170881570 hasConcept C9417928 @default.
• W3170881570 hasConceptScore W3170881570C104317684 @default.
• W3170881570 hasConceptScore W3170881570C106430172 @default.
• W3170881570 hasConceptScore W3170881570C108583219 @default.
• W3170881570 hasConceptScore W3170881570C11413529 @default.
• W3170881570 hasConceptScore W3170881570C115961682 @default.
• W3170881570 hasConceptScore W3170881570C124851039 @default.
• W3170881570 hasConceptScore W3170881570C141379421 @default.
• W3170881570 hasConceptScore W3170881570C153180895 @default.
• W3170881570 hasConceptScore W3170881570C154945302 @default.

• next