Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386598498> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4386598498 abstract "In practical hyperspectral image (HSI) classification tasks, we often encounter the problems of few-shot classification and domain misalignment between source domains and target domains. To solve this classification paradigm, a meta-learning method of few-shot learning (FSL) is usually used. However, most existing FSL methods address the problem for domain alignment and neglect the exploration of semantic relationships of objects across domains. In this paper, we propose the cross-domain spectral semantic transformer FSL (SSTFSL), which can fully extract semantic features and spectral detail features for the cross-domain few-shot HSI classification task. Specifically, the multi-head self-attention (MSA) mechanism with enhancement process (EP) of the transformer is used to map out semantically relevant local regions and can enhance the ability of the model to distinguish subtle feature differences in the spectrum. In addition, the matching degree of different branches is computed by relational network learning, which ultimately enables cross-domain few-shot HSI classification. Through extensive experiments, we evaluate the classification performance of SSTFSL on HSI datasets. The results demonstrate that SSTFSL outperforms existing FSL methods and deep learning methods on HSI classification." @default.
- W4386598498 created "2023-09-12" @default.
- W4386598498 creator A5013015632 @default.
- W4386598498 creator A5037048102 @default.
- W4386598498 creator A5048495519 @default.
- W4386598498 creator A5057996314 @default.
- W4386598498 creator A5072886785 @default.
- W4386598498 creator A5082599371 @default.
- W4386598498 date "2023-10-08" @default.
- W4386598498 modified "2023-09-27" @default.
- W4386598498 title "Few-Shot Hyperspectral Image Classification Based on Cross-Domain Spectral Semantic Relation Transformer" @default.
- W4386598498 cites W2500751094 @default.
- W4386598498 cites W2572303978 @default.
- W4386598498 cites W2764276316 @default.
- W4386598498 cites W2788776964 @default.
- W4386598498 cites W2898204262 @default.
- W4386598498 cites W3012405452 @default.
- W4386598498 cites W3023991509 @default.
- W4386598498 cites W3047443805 @default.
- W4386598498 cites W3101640299 @default.
- W4386598498 cites W3127230150 @default.
- W4386598498 cites W3132867842 @default.
- W4386598498 cites W4221151152 @default.
- W4386598498 cites W4224938958 @default.
- W4386598498 cites W4225931144 @default.
- W4386598498 cites W4283834642 @default.
- W4386598498 cites W4286484203 @default.
- W4386598498 cites W4288054357 @default.
- W4386598498 cites W4308236992 @default.
- W4386598498 cites W4308238079 @default.
- W4386598498 doi "https://doi.org/10.1109/icip49359.2023.10222564" @default.
- W4386598498 hasPublicationYear "2023" @default.
- W4386598498 type Work @default.
- W4386598498 citedByCount "0" @default.
- W4386598498 crossrefType "proceedings-article" @default.
- W4386598498 hasAuthorship W4386598498A5013015632 @default.
- W4386598498 hasAuthorship W4386598498A5037048102 @default.
- W4386598498 hasAuthorship W4386598498A5048495519 @default.
- W4386598498 hasAuthorship W4386598498A5057996314 @default.
- W4386598498 hasAuthorship W4386598498A5072886785 @default.
- W4386598498 hasAuthorship W4386598498A5082599371 @default.
- W4386598498 hasBestOaLocation W43865984981 @default.
- W4386598498 hasConcept C115961682 @default.
- W4386598498 hasConcept C119857082 @default.
- W4386598498 hasConcept C121332964 @default.
- W4386598498 hasConcept C12267149 @default.
- W4386598498 hasConcept C153180895 @default.
- W4386598498 hasConcept C154945302 @default.
- W4386598498 hasConcept C159078339 @default.
- W4386598498 hasConcept C165801399 @default.
- W4386598498 hasConcept C41008148 @default.
- W4386598498 hasConcept C52622490 @default.
- W4386598498 hasConcept C62520636 @default.
- W4386598498 hasConcept C66322947 @default.
- W4386598498 hasConcept C75294576 @default.
- W4386598498 hasConceptScore W4386598498C115961682 @default.
- W4386598498 hasConceptScore W4386598498C119857082 @default.
- W4386598498 hasConceptScore W4386598498C121332964 @default.
- W4386598498 hasConceptScore W4386598498C12267149 @default.
- W4386598498 hasConceptScore W4386598498C153180895 @default.
- W4386598498 hasConceptScore W4386598498C154945302 @default.
- W4386598498 hasConceptScore W4386598498C159078339 @default.
- W4386598498 hasConceptScore W4386598498C165801399 @default.
- W4386598498 hasConceptScore W4386598498C41008148 @default.
- W4386598498 hasConceptScore W4386598498C52622490 @default.
- W4386598498 hasConceptScore W4386598498C62520636 @default.
- W4386598498 hasConceptScore W4386598498C66322947 @default.
- W4386598498 hasConceptScore W4386598498C75294576 @default.
- W4386598498 hasFunder F4320321001 @default.
- W4386598498 hasFunder F4320324174 @default.
- W4386598498 hasFunder F4320324887 @default.
- W4386598498 hasLocation W43865984981 @default.
- W4386598498 hasOpenAccess W4386598498 @default.
- W4386598498 hasPrimaryLocation W43865984981 @default.
- W4386598498 hasRelatedWork W1591029852 @default.
- W4386598498 hasRelatedWork W2051197289 @default.
- W4386598498 hasRelatedWork W2056016498 @default.
- W4386598498 hasRelatedWork W2336974148 @default.
- W4386598498 hasRelatedWork W2738461075 @default.
- W4386598498 hasRelatedWork W2940977206 @default.
- W4386598498 hasRelatedWork W3005023910 @default.
- W4386598498 hasRelatedWork W3131722669 @default.
- W4386598498 hasRelatedWork W3173596272 @default.
- W4386598498 hasRelatedWork W2345184372 @default.
- W4386598498 isParatext "false" @default.
- W4386598498 isRetracted "false" @default.
- W4386598498 workType "article" @default.