Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387492302> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4387492302 endingPage "104237" @default.
- W4387492302 startingPage "104237" @default.
- W4387492302 abstract "Convolutional neural network (CNN) and its variants have been widely applied to hyperspectral classification for their excellent ability to extract local features. However, as research on hyperspectral imaging (HSI) has progressed, CNNs have been proven to struggle in extracting and representing the sequential properties of spectral characteristics. Recently, some researchers have demonstrated the feasibility of transformer architecture in HSI classification due to its powerful ability to characterize spectral information. The lack of suitable pre-processing and optimization methods which are used for the transformer's application in HSI becomes a major limitation to model's performance. Therefore, to enhance model's performance and practicality, we propose an efficient transformer backbone for HSI classification, named Efficient-Spectralformer. In the proposed framework, we rethink the input form and design the Split Grouping Embedding (SGE) module that requires much less computational resources. Additionally, to maximize the use of attentional feature information from different layers, we have used the Multi-layer Feature Fusion (MFF) module is used to learn multi-layer spectral attention information. The experiments conducted on five HSI datasets demonstrate that the proposed method achieves better performance under much less memory usage (about 30% of the original on average) by comparing with the original Spectralformer." @default.
- W4387492302 created "2023-10-11" @default.
- W4387492302 creator A5014445473 @default.
- W4387492302 creator A5037575655 @default.
- W4387492302 creator A5058012950 @default.
- W4387492302 creator A5069292806 @default.
- W4387492302 creator A5081305410 @default.
- W4387492302 date "2023-10-01" @default.
- W4387492302 modified "2023-10-16" @default.
- W4387492302 title "Efficient SpectralFormer for Hyperspectral Image Classification" @default.
- W4387492302 cites W1901129140 @default.
- W4387492302 cites W1903029394 @default.
- W4387492302 cites W1992813404 @default.
- W4387492302 cites W2025522544 @default.
- W4387492302 cites W2029316659 @default.
- W4387492302 cites W2037236246 @default.
- W4387492302 cites W2136251662 @default.
- W4387492302 cites W2158400785 @default.
- W4387492302 cites W2166923144 @default.
- W4387492302 cites W2465503420 @default.
- W4387492302 cites W2514028694 @default.
- W4387492302 cites W2565639579 @default.
- W4387492302 cites W2598997103 @default.
- W4387492302 cites W2767198899 @default.
- W4387492302 cites W2886666371 @default.
- W4387492302 cites W2888119354 @default.
- W4387492302 cites W2963446712 @default.
- W4387492302 cites W2987619624 @default.
- W4387492302 cites W2997343747 @default.
- W4387492302 cites W3037458146 @default.
- W4387492302 cites W3047443805 @default.
- W4387492302 cites W3094897602 @default.
- W4387492302 cites W3100011500 @default.
- W4387492302 cites W3101640299 @default.
- W4387492302 cites W3122774149 @default.
- W4387492302 cites W3181729304 @default.
- W4387492302 cites W3191251640 @default.
- W4387492302 cites W3214821343 @default.
- W4387492302 cites W4214713996 @default.
- W4387492302 cites W4285124290 @default.
- W4387492302 cites W4313046455 @default.
- W4387492302 doi "https://doi.org/10.1016/j.dsp.2023.104237" @default.
- W4387492302 hasPublicationYear "2023" @default.
- W4387492302 type Work @default.
- W4387492302 citedByCount "0" @default.
- W4387492302 crossrefType "journal-article" @default.
- W4387492302 hasAuthorship W4387492302A5014445473 @default.
- W4387492302 hasAuthorship W4387492302A5037575655 @default.
- W4387492302 hasAuthorship W4387492302A5058012950 @default.
- W4387492302 hasAuthorship W4387492302A5069292806 @default.
- W4387492302 hasAuthorship W4387492302A5081305410 @default.
- W4387492302 hasConcept C121332964 @default.
- W4387492302 hasConcept C138885662 @default.
- W4387492302 hasConcept C153180895 @default.
- W4387492302 hasConcept C154945302 @default.
- W4387492302 hasConcept C159078339 @default.
- W4387492302 hasConcept C165801399 @default.
- W4387492302 hasConcept C2776401178 @default.
- W4387492302 hasConcept C41008148 @default.
- W4387492302 hasConcept C41608201 @default.
- W4387492302 hasConcept C41895202 @default.
- W4387492302 hasConcept C52622490 @default.
- W4387492302 hasConcept C62520636 @default.
- W4387492302 hasConcept C66322947 @default.
- W4387492302 hasConcept C81363708 @default.
- W4387492302 hasConceptScore W4387492302C121332964 @default.
- W4387492302 hasConceptScore W4387492302C138885662 @default.
- W4387492302 hasConceptScore W4387492302C153180895 @default.
- W4387492302 hasConceptScore W4387492302C154945302 @default.
- W4387492302 hasConceptScore W4387492302C159078339 @default.
- W4387492302 hasConceptScore W4387492302C165801399 @default.
- W4387492302 hasConceptScore W4387492302C2776401178 @default.
- W4387492302 hasConceptScore W4387492302C41008148 @default.
- W4387492302 hasConceptScore W4387492302C41608201 @default.
- W4387492302 hasConceptScore W4387492302C41895202 @default.
- W4387492302 hasConceptScore W4387492302C52622490 @default.
- W4387492302 hasConceptScore W4387492302C62520636 @default.
- W4387492302 hasConceptScore W4387492302C66322947 @default.
- W4387492302 hasConceptScore W4387492302C81363708 @default.
- W4387492302 hasLocation W43874923021 @default.
- W4387492302 hasOpenAccess W4387492302 @default.
- W4387492302 hasPrimaryLocation W43874923021 @default.
- W4387492302 hasRelatedWork W2019190440 @default.
- W4387492302 hasRelatedWork W2027399350 @default.
- W4387492302 hasRelatedWork W2044184146 @default.
- W4387492302 hasRelatedWork W2060875994 @default.
- W4387492302 hasRelatedWork W2070598848 @default.
- W4387492302 hasRelatedWork W2072166414 @default.
- W4387492302 hasRelatedWork W3034375524 @default.
- W4387492302 hasRelatedWork W3034864990 @default.
- W4387492302 hasRelatedWork W3209970181 @default.
- W4387492302 hasRelatedWork W4230131218 @default.
- W4387492302 isParatext "false" @default.
- W4387492302 isRetracted "false" @default.
- W4387492302 workType "article" @default.