Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381384195> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4381384195 endingPage "104120" @default.
- W4381384195 startingPage "104120" @default.
- W4381384195 abstract "Deep learning based compressed sensing imaging algorithms usually adopt supervised learning mechanism, which generally require massive high-quality images paired with the measured data in the training process. However, clear images are difficult to obtain in some specific application scenarios. In view of this, we propose a self-attention powered multi-scale compressed sensing imaging network named BNN-SANet with the Bayesian self-supervised learning manner in this paper. BNN-SANet can automatically learn effective feature representation from the measured data and reconstruct high-quality images without large-scale training samples. In particular, the self-attention based Transformer employed in BNN-SANet is effective to exploit global and long-range dependencies. Multi-scale dual path design in BNN-SANet performs well in extracting the semantic information at different scales to further improve the CS reconstruction quality. Experimental results illustrate that the proposed approach is substantially superior to previous compressed sensing imaging methods in terms of Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM) and visual metrics." @default.
- W4381384195 created "2023-06-21" @default.
- W4381384195 creator A5005774249 @default.
- W4381384195 creator A5040131574 @default.
- W4381384195 creator A5069826751 @default.
- W4381384195 creator A5078313753 @default.
- W4381384195 date "2023-08-01" @default.
- W4381384195 modified "2023-09-27" @default.
- W4381384195 title "Bayesian self-supervised learning allying with Transformer powered compressed sensing imaging" @default.
- W4381384195 cites W1968773088 @default.
- W4381384195 cites W2018990310 @default.
- W4381384195 cites W2056370875 @default.
- W4381384195 cites W2082029531 @default.
- W4381384195 cites W2128692736 @default.
- W4381384195 cites W2130120519 @default.
- W4381384195 cites W2145096794 @default.
- W4381384195 cites W2164452299 @default.
- W4381384195 cites W2289917018 @default.
- W4381384195 cites W2590877996 @default.
- W4381384195 cites W2884520723 @default.
- W4381384195 cites W2896927224 @default.
- W4381384195 cites W2898375653 @default.
- W4381384195 cites W2916894988 @default.
- W4381384195 cites W2939110275 @default.
- W4381384195 cites W2963676935 @default.
- W4381384195 cites W2964859579 @default.
- W4381384195 cites W3100456687 @default.
- W4381384195 cites W4250955649 @default.
- W4381384195 cites W4285082149 @default.
- W4381384195 cites W4288046542 @default.
- W4381384195 cites W4318767904 @default.
- W4381384195 doi "https://doi.org/10.1016/j.dsp.2023.104120" @default.
- W4381384195 hasPublicationYear "2023" @default.
- W4381384195 type Work @default.
- W4381384195 citedByCount "0" @default.
- W4381384195 crossrefType "journal-article" @default.
- W4381384195 hasAuthorship W4381384195A5005774249 @default.
- W4381384195 hasAuthorship W4381384195A5040131574 @default.
- W4381384195 hasAuthorship W4381384195A5069826751 @default.
- W4381384195 hasAuthorship W4381384195A5078313753 @default.
- W4381384195 hasConcept C107673813 @default.
- W4381384195 hasConcept C108583219 @default.
- W4381384195 hasConcept C119857082 @default.
- W4381384195 hasConcept C124851039 @default.
- W4381384195 hasConcept C136389625 @default.
- W4381384195 hasConcept C153180895 @default.
- W4381384195 hasConcept C154945302 @default.
- W4381384195 hasConcept C165696696 @default.
- W4381384195 hasConcept C38652104 @default.
- W4381384195 hasConcept C41008148 @default.
- W4381384195 hasConcept C50644808 @default.
- W4381384195 hasConcept C59404180 @default.
- W4381384195 hasConceptScore W4381384195C107673813 @default.
- W4381384195 hasConceptScore W4381384195C108583219 @default.
- W4381384195 hasConceptScore W4381384195C119857082 @default.
- W4381384195 hasConceptScore W4381384195C124851039 @default.
- W4381384195 hasConceptScore W4381384195C136389625 @default.
- W4381384195 hasConceptScore W4381384195C153180895 @default.
- W4381384195 hasConceptScore W4381384195C154945302 @default.
- W4381384195 hasConceptScore W4381384195C165696696 @default.
- W4381384195 hasConceptScore W4381384195C38652104 @default.
- W4381384195 hasConceptScore W4381384195C41008148 @default.
- W4381384195 hasConceptScore W4381384195C50644808 @default.
- W4381384195 hasConceptScore W4381384195C59404180 @default.
- W4381384195 hasLocation W43813841951 @default.
- W4381384195 hasOpenAccess W4381384195 @default.
- W4381384195 hasPrimaryLocation W43813841951 @default.
- W4381384195 hasRelatedWork W3192794374 @default.
- W4381384195 hasRelatedWork W4220686584 @default.
- W4381384195 hasRelatedWork W4221136938 @default.
- W4381384195 hasRelatedWork W4223943233 @default.
- W4381384195 hasRelatedWork W4246751904 @default.
- W4381384195 hasRelatedWork W4312200629 @default.
- W4381384195 hasRelatedWork W4360585206 @default.
- W4381384195 hasRelatedWork W4364306694 @default.
- W4381384195 hasRelatedWork W4380075502 @default.
- W4381384195 hasRelatedWork W4380086463 @default.
- W4381384195 hasVolume "140" @default.
- W4381384195 isParatext "false" @default.
- W4381384195 isRetracted "false" @default.
- W4381384195 workType "article" @default.