Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312463027> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4312463027 abstract "Recent advances in deep learning (DL) reveal that the structure of a convolutional neural network (CNN) is a good image prior (called deep image prior (DIP)), bridging the model-based and DL-based methods in image restoration. However, optimizing a DIP-based CNN is prone to over-fitting leading to a poorly reconstructed image. This paper derives a loss function based on Stein's unbiased risk estimate (SURE) for unsupervised training of a DIP-based CNN applied to the hyperspectral image (HSI) super-resolution. The SURE loss function is an unbiased estimate of the mean-square-error (MSE) between the clean low-resolution image and the low-resolution estimated image, which relies only on the observed low-resolution image. Experimental results on HSI show that the proposed method not only improves the performance, but also avoids overfitting. Codes are available at https://github.com/hvn2/SURE-MS-HS" @default.
- W4312463027 created "2023-01-04" @default.
- W4312463027 creator A5008277487 @default.
- W4312463027 creator A5050760333 @default.
- W4312463027 creator A5069292094 @default.
- W4312463027 creator A5083502204 @default.
- W4312463027 date "2022-07-17" @default.
- W4312463027 modified "2023-10-17" @default.
- W4312463027 title "Hyperspectral Super-Resolution by Unsupervised Convolutional Neural Network and Sure" @default.
- W4312463027 cites W2021046129 @default.
- W4312463027 cites W2054640142 @default.
- W4312463027 cites W2070424424 @default.
- W4312463027 cites W2120466359 @default.
- W4312463027 cites W2145568341 @default.
- W4312463027 cites W2494274259 @default.
- W4312463027 cites W2592312604 @default.
- W4312463027 cites W2771305881 @default.
- W4312463027 cites W2998841120 @default.
- W4312463027 cites W3043719198 @default.
- W4312463027 cites W3107490592 @default.
- W4312463027 cites W3123265576 @default.
- W4312463027 cites W4229685799 @default.
- W4312463027 doi "https://doi.org/10.1109/igarss46834.2022.9883576" @default.
- W4312463027 hasPublicationYear "2022" @default.
- W4312463027 type Work @default.
- W4312463027 citedByCount "1" @default.
- W4312463027 countsByYear W43124630272023 @default.
- W4312463027 crossrefType "proceedings-article" @default.
- W4312463027 hasAuthorship W4312463027A5008277487 @default.
- W4312463027 hasAuthorship W4312463027A5050760333 @default.
- W4312463027 hasAuthorship W4312463027A5069292094 @default.
- W4312463027 hasAuthorship W4312463027A5083502204 @default.
- W4312463027 hasConcept C105795698 @default.
- W4312463027 hasConcept C108583219 @default.
- W4312463027 hasConcept C115961682 @default.
- W4312463027 hasConcept C139945424 @default.
- W4312463027 hasConcept C141239990 @default.
- W4312463027 hasConcept C153180895 @default.
- W4312463027 hasConcept C154945302 @default.
- W4312463027 hasConcept C159078339 @default.
- W4312463027 hasConcept C205372480 @default.
- W4312463027 hasConcept C22019652 @default.
- W4312463027 hasConcept C33923547 @default.
- W4312463027 hasConcept C41008148 @default.
- W4312463027 hasConcept C50644808 @default.
- W4312463027 hasConcept C81363708 @default.
- W4312463027 hasConceptScore W4312463027C105795698 @default.
- W4312463027 hasConceptScore W4312463027C108583219 @default.
- W4312463027 hasConceptScore W4312463027C115961682 @default.
- W4312463027 hasConceptScore W4312463027C139945424 @default.
- W4312463027 hasConceptScore W4312463027C141239990 @default.
- W4312463027 hasConceptScore W4312463027C153180895 @default.
- W4312463027 hasConceptScore W4312463027C154945302 @default.
- W4312463027 hasConceptScore W4312463027C159078339 @default.
- W4312463027 hasConceptScore W4312463027C205372480 @default.
- W4312463027 hasConceptScore W4312463027C22019652 @default.
- W4312463027 hasConceptScore W4312463027C33923547 @default.
- W4312463027 hasConceptScore W4312463027C41008148 @default.
- W4312463027 hasConceptScore W4312463027C50644808 @default.
- W4312463027 hasConceptScore W4312463027C81363708 @default.
- W4312463027 hasFunder F4320323298 @default.
- W4312463027 hasLocation W43124630271 @default.
- W4312463027 hasOpenAccess W4312463027 @default.
- W4312463027 hasPrimaryLocation W43124630271 @default.
- W4312463027 hasRelatedWork W2766146978 @default.
- W4312463027 hasRelatedWork W2807839383 @default.
- W4312463027 hasRelatedWork W2997709384 @default.
- W4312463027 hasRelatedWork W3173596272 @default.
- W4312463027 hasRelatedWork W4200550458 @default.
- W4312463027 hasRelatedWork W4220996320 @default.
- W4312463027 hasRelatedWork W4283701629 @default.
- W4312463027 hasRelatedWork W4309224979 @default.
- W4312463027 hasRelatedWork W4313289428 @default.
- W4312463027 hasRelatedWork W4321439147 @default.
- W4312463027 isParatext "false" @default.
- W4312463027 isRetracted "false" @default.
- W4312463027 workType "article" @default.