Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367682132> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4367682132 endingPage "044503" @default.
- W4367682132 startingPage "044503" @default.
- W4367682132 abstract "Abstract Traditional stellar classification methods include spectral and photometric classification separately. Although satisfactory results can be achieved, the accuracy could be improved. In this paper, we pioneer a novel approach to deeply fuse the spectra and photometric images of the sources in an advanced multimodal network to enhance the model’s discriminatory ability. We use Transformer as the fusion module and apply a spectrum–image contrastive loss function to enhance the consistency of the spectrum and photometric image of the same source in two different feature spaces. We perform M-type stellar subtype classification on two data sets with high and low signal-to-noise ratio (S/N) spectra and corresponding photometric images, and the F1-score achieves 95.65% and 90.84%, respectively. In our experiments, we prove that our model effectively utilizes the information from photometric images and is more accurate than advanced spectrum and photometric image classifiers. Our contributions can be summarized as follows: (1) We propose an innovative idea for stellar classification that allows the model to simultaneously consider information from spectra and photometric images. (2) We discover the challenge of fusing low-S/N spectra and photometric images in the Transformer and provide a solution. (3) The effectiveness of Transformer for spectral classification is discussed for the first time and will inspire more Transformer-based spectral classification models." @default.
- W4367682132 created "2023-05-03" @default.
- W4367682132 creator A5005936929 @default.
- W4367682132 creator A5006467926 @default.
- W4367682132 creator A5008984910 @default.
- W4367682132 creator A5014549960 @default.
- W4367682132 creator A5021642223 @default.
- W4367682132 date "2023-04-01" @default.
- W4367682132 modified "2023-10-13" @default.
- W4367682132 title "Deep Multimodal Networks for M-type Star Classification with Paired Spectrum and Photometric Image" @default.
- W4367682132 cites W1979379324 @default.
- W4367682132 cites W2044738244 @default.
- W4367682132 cites W2150331774 @default.
- W4367682132 cites W2155488926 @default.
- W4367682132 cites W2157917411 @default.
- W4367682132 cites W2345631583 @default.
- W4367682132 cites W2562512660 @default.
- W4367682132 cites W2619383789 @default.
- W4367682132 cites W2794345050 @default.
- W4367682132 cites W2885274016 @default.
- W4367682132 cites W2985076077 @default.
- W4367682132 cites W2987499710 @default.
- W4367682132 cites W3010823851 @default.
- W4367682132 cites W3032874046 @default.
- W4367682132 cites W3098166093 @default.
- W4367682132 cites W3170297088 @default.
- W4367682132 cites W3184679245 @default.
- W4367682132 cites W3198196812 @default.
- W4367682132 cites W4308671849 @default.
- W4367682132 cites W4308840577 @default.
- W4367682132 cites W4310500628 @default.
- W4367682132 cites W4318033792 @default.
- W4367682132 cites W2900169724 @default.
- W4367682132 doi "https://doi.org/10.1088/1538-3873/acc7ca" @default.
- W4367682132 hasPublicationYear "2023" @default.
- W4367682132 type Work @default.
- W4367682132 citedByCount "1" @default.
- W4367682132 crossrefType "journal-article" @default.
- W4367682132 hasAuthorship W4367682132A5005936929 @default.
- W4367682132 hasAuthorship W4367682132A5006467926 @default.
- W4367682132 hasAuthorship W4367682132A5008984910 @default.
- W4367682132 hasAuthorship W4367682132A5014549960 @default.
- W4367682132 hasAuthorship W4367682132A5021642223 @default.
- W4367682132 hasConcept C121332964 @default.
- W4367682132 hasConcept C1276947 @default.
- W4367682132 hasConcept C150846664 @default.
- W4367682132 hasConcept C153180895 @default.
- W4367682132 hasConcept C154945302 @default.
- W4367682132 hasConcept C180690934 @default.
- W4367682132 hasConcept C31972630 @default.
- W4367682132 hasConcept C41008148 @default.
- W4367682132 hasConcept C4839761 @default.
- W4367682132 hasConcept C68271606 @default.
- W4367682132 hasConceptScore W4367682132C121332964 @default.
- W4367682132 hasConceptScore W4367682132C1276947 @default.
- W4367682132 hasConceptScore W4367682132C150846664 @default.
- W4367682132 hasConceptScore W4367682132C153180895 @default.
- W4367682132 hasConceptScore W4367682132C154945302 @default.
- W4367682132 hasConceptScore W4367682132C180690934 @default.
- W4367682132 hasConceptScore W4367682132C31972630 @default.
- W4367682132 hasConceptScore W4367682132C41008148 @default.
- W4367682132 hasConceptScore W4367682132C4839761 @default.
- W4367682132 hasConceptScore W4367682132C68271606 @default.
- W4367682132 hasFunder F4320321001 @default.
- W4367682132 hasIssue "1046" @default.
- W4367682132 hasLocation W43676821321 @default.
- W4367682132 hasOpenAccess W4367682132 @default.
- W4367682132 hasPrimaryLocation W43676821321 @default.
- W4367682132 hasRelatedWork W1489909445 @default.
- W4367682132 hasRelatedWork W1917325541 @default.
- W4367682132 hasRelatedWork W2042388928 @default.
- W4367682132 hasRelatedWork W2066141776 @default.
- W4367682132 hasRelatedWork W2073774881 @default.
- W4367682132 hasRelatedWork W2075501916 @default.
- W4367682132 hasRelatedWork W2086843505 @default.
- W4367682132 hasRelatedWork W2088391470 @default.
- W4367682132 hasRelatedWork W3010401860 @default.
- W4367682132 hasRelatedWork W3017238984 @default.
- W4367682132 hasVolume "135" @default.
- W4367682132 isParatext "false" @default.
- W4367682132 isRetracted "false" @default.
- W4367682132 workType "article" @default.