Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136605212> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3136605212 abstract "Spectral reconstruction (SR) algorithms attempt to map RGB- to hyperspectral-images. Classically, simple pixel-based regression is used to solve for this SR mapping and more recently patch-based Deep Neural Networks (DNN) are considered (with a modest performance increment). For either method, the 'training' process typically minimizes a Mean-Squared-Error (MSE) loss. Curiously, in recent research, SR algorithms are evaluated and ranked based on a relative percentage error, so-called MeanRelative-Absolute Error (MRAE), which behaves very differently from the MSE loss function. The most recent DNN approaches - perhaps unsurprisingly - directly optimize for this new MRAE error in training so as to match this new evaluation criteria.<br/> In this paper, we show how we can also reformulate pixelbased regression methods so that they too optimize a relative spectral error. Our Relative Error Least-Squares (RELS) approach minimizes an error that is similar to MRAE. Experiments demonstrate that regression models based on RELS deliver better spectral recovery, with up to a 10% increment in mean performance and a 20% improvement in worst-case performance depending on the method." @default.
- W3136605212 created "2021-03-29" @default.
- W3136605212 creator A5043339662 @default.
- W3136605212 creator A5080437616 @default.
- W3136605212 date "2020-11-04" @default.
- W3136605212 modified "2023-10-16" @default.
- W3136605212 title "Reconstructing Spectra from RGB Images by Relative Error Least-Squares Regression" @default.
- W3136605212 cites W1517606245 @default.
- W3136605212 cites W1990895816 @default.
- W3136605212 cites W1991724284 @default.
- W3136605212 cites W1999331929 @default.
- W3136605212 cites W2085765819 @default.
- W3136605212 cites W2090424610 @default.
- W3136605212 cites W2106277226 @default.
- W3136605212 cites W2116641053 @default.
- W3136605212 cites W2461301037 @default.
- W3136605212 cites W2512266304 @default.
- W3136605212 cites W2520302833 @default.
- W3136605212 cites W2520430674 @default.
- W3136605212 cites W2766419681 @default.
- W3136605212 cites W2767054107 @default.
- W3136605212 cites W2893739000 @default.
- W3136605212 cites W2901677542 @default.
- W3136605212 cites W2902415664 @default.
- W3136605212 cites W2981374059 @default.
- W3136605212 cites W2990678607 @default.
- W3136605212 cites W3011076973 @default.
- W3136605212 cites W3122360337 @default.
- W3136605212 doi "https://doi.org/10.2352/issn.2169-2629.2020.28.42" @default.
- W3136605212 hasPublicationYear "2020" @default.
- W3136605212 type Work @default.
- W3136605212 sameAs 3136605212 @default.
- W3136605212 citedByCount "0" @default.
- W3136605212 crossrefType "journal-article" @default.
- W3136605212 hasAuthorship W3136605212A5043339662 @default.
- W3136605212 hasAuthorship W3136605212A5080437616 @default.
- W3136605212 hasBestOaLocation W31366052121 @default.
- W3136605212 hasConcept C105795698 @default.
- W3136605212 hasConcept C11413529 @default.
- W3136605212 hasConcept C119857082 @default.
- W3136605212 hasConcept C122383733 @default.
- W3136605212 hasConcept C139945424 @default.
- W3136605212 hasConcept C154945302 @default.
- W3136605212 hasConcept C159078339 @default.
- W3136605212 hasConcept C160633673 @default.
- W3136605212 hasConcept C185429906 @default.
- W3136605212 hasConcept C188154048 @default.
- W3136605212 hasConcept C33923547 @default.
- W3136605212 hasConcept C41008148 @default.
- W3136605212 hasConcept C50644808 @default.
- W3136605212 hasConcept C82990744 @default.
- W3136605212 hasConcept C83546350 @default.
- W3136605212 hasConcept C9936470 @default.
- W3136605212 hasConcept C99656134 @default.
- W3136605212 hasConceptScore W3136605212C105795698 @default.
- W3136605212 hasConceptScore W3136605212C11413529 @default.
- W3136605212 hasConceptScore W3136605212C119857082 @default.
- W3136605212 hasConceptScore W3136605212C122383733 @default.
- W3136605212 hasConceptScore W3136605212C139945424 @default.
- W3136605212 hasConceptScore W3136605212C154945302 @default.
- W3136605212 hasConceptScore W3136605212C159078339 @default.
- W3136605212 hasConceptScore W3136605212C160633673 @default.
- W3136605212 hasConceptScore W3136605212C185429906 @default.
- W3136605212 hasConceptScore W3136605212C188154048 @default.
- W3136605212 hasConceptScore W3136605212C33923547 @default.
- W3136605212 hasConceptScore W3136605212C41008148 @default.
- W3136605212 hasConceptScore W3136605212C50644808 @default.
- W3136605212 hasConceptScore W3136605212C82990744 @default.
- W3136605212 hasConceptScore W3136605212C83546350 @default.
- W3136605212 hasConceptScore W3136605212C9936470 @default.
- W3136605212 hasConceptScore W3136605212C99656134 @default.
- W3136605212 hasLocation W31366052121 @default.
- W3136605212 hasLocation W31366052122 @default.
- W3136605212 hasOpenAccess W3136605212 @default.
- W3136605212 hasPrimaryLocation W31366052121 @default.
- W3136605212 hasRelatedWork W12139544 @default.
- W3136605212 hasRelatedWork W13273322 @default.
- W3136605212 hasRelatedWork W13815759 @default.
- W3136605212 hasRelatedWork W14579021 @default.
- W3136605212 hasRelatedWork W14587445 @default.
- W3136605212 hasRelatedWork W5896900 @default.
- W3136605212 hasRelatedWork W6873763 @default.
- W3136605212 hasRelatedWork W7591744 @default.
- W3136605212 hasRelatedWork W8844810 @default.
- W3136605212 hasRelatedWork W3674366 @default.
- W3136605212 isParatext "false" @default.
- W3136605212 isRetracted "false" @default.
- W3136605212 magId "3136605212" @default.
- W3136605212 workType "article" @default.