Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366992324> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4366992324 endingPage "2494" @default.
- W4366992324 startingPage "2480" @default.
- W4366992324 abstract "Deep learning methods have shown great advantages in hyperspectral image (HSI) classification tasks. In particular, convolutional neural network (CNN)-based methods for HSI classification have made great progress. However, it is difficult for CNN to process long-range spatial and spectral information. Recently, a novel deep learning model called transformer has demonstrated its potential to replace CNN in various classification tasks with its amazing performance. In this letter, a multi-scale spectral-spatial dual-transformer network (MS3DT) is proposed to deeply consider the spectral-spatial features via transformer. Specifically, MS3DT consists of a feature pyramid network (FPN), a spectral transformer subnetwork (SPECT) and a spatial transformer subnetwork (SPAT). To utilize the complementary multi-scale characteristics, we introduce FPN to capture shallow-to-deep and spectral-spatial features. To improve the representational capacity in spatial and spectral domains, SPECT is exploited to extract long-range spectral correlation over local spectral features, and SPAT is designed to explore the contextual information for better refinement. Therefore, MS3DT is able to adaptively recalibrate the nonlinear interdependence of shallow-to-deep spectral-spatial features by merging the two subnetworks. Experiments on two widely used HSI datasets show that the MS3DT can outperform the state-of-the-art (SOTA) algorithm. The source codes will be available at https://github.com/RsAI-lab/MSSSDT." @default.
- W4366992324 created "2023-04-27" @default.
- W4366992324 creator A5024631382 @default.
- W4366992324 creator A5030269700 @default.
- W4366992324 creator A5052029726 @default.
- W4366992324 creator A5053518414 @default.
- W4366992324 creator A5074984354 @default.
- W4366992324 creator A5075063437 @default.
- W4366992324 date "2023-04-03" @default.
- W4366992324 modified "2023-09-25" @default.
- W4366992324 title "Multi-scale spectral-spatial dual-transformer network for hyperspectral image classification" @default.
- W4366992324 cites W2006175358 @default.
- W4366992324 cites W2044439250 @default.
- W4366992324 cites W2114819256 @default.
- W4366992324 cites W2169500530 @default.
- W4366992324 cites W2764276316 @default.
- W4366992324 cites W2765739551 @default.
- W4366992324 cites W2822065499 @default.
- W4366992324 cites W2884585870 @default.
- W4366992324 cites W2948157022 @default.
- W4366992324 cites W2963420686 @default.
- W4366992324 cites W2977002487 @default.
- W4366992324 cites W3003326148 @default.
- W4366992324 cites W3022254425 @default.
- W4366992324 cites W3031696400 @default.
- W4366992324 cites W3105357426 @default.
- W4366992324 cites W3105553032 @default.
- W4366992324 cites W3189718454 @default.
- W4366992324 cites W3193242948 @default.
- W4366992324 cites W3205965083 @default.
- W4366992324 cites W4210794570 @default.
- W4366992324 cites W4214654781 @default.
- W4366992324 cites W4285187901 @default.
- W4366992324 cites W4313029572 @default.
- W4366992324 doi "https://doi.org/10.1080/01431161.2023.2203340" @default.
- W4366992324 hasPublicationYear "2023" @default.
- W4366992324 type Work @default.
- W4366992324 citedByCount "1" @default.
- W4366992324 countsByYear W43669923242023 @default.
- W4366992324 crossrefType "journal-article" @default.
- W4366992324 hasAuthorship W4366992324A5024631382 @default.
- W4366992324 hasAuthorship W4366992324A5030269700 @default.
- W4366992324 hasAuthorship W4366992324A5052029726 @default.
- W4366992324 hasAuthorship W4366992324A5053518414 @default.
- W4366992324 hasAuthorship W4366992324A5074984354 @default.
- W4366992324 hasAuthorship W4366992324A5075063437 @default.
- W4366992324 hasConcept C108583219 @default.
- W4366992324 hasConcept C121332964 @default.
- W4366992324 hasConcept C127313418 @default.
- W4366992324 hasConcept C153180895 @default.
- W4366992324 hasConcept C154945302 @default.
- W4366992324 hasConcept C159078339 @default.
- W4366992324 hasConcept C159620131 @default.
- W4366992324 hasConcept C165801399 @default.
- W4366992324 hasConcept C2780186347 @default.
- W4366992324 hasConcept C38652104 @default.
- W4366992324 hasConcept C41008148 @default.
- W4366992324 hasConcept C62520636 @default.
- W4366992324 hasConcept C62649853 @default.
- W4366992324 hasConcept C66322947 @default.
- W4366992324 hasConcept C81363708 @default.
- W4366992324 hasConceptScore W4366992324C108583219 @default.
- W4366992324 hasConceptScore W4366992324C121332964 @default.
- W4366992324 hasConceptScore W4366992324C127313418 @default.
- W4366992324 hasConceptScore W4366992324C153180895 @default.
- W4366992324 hasConceptScore W4366992324C154945302 @default.
- W4366992324 hasConceptScore W4366992324C159078339 @default.
- W4366992324 hasConceptScore W4366992324C159620131 @default.
- W4366992324 hasConceptScore W4366992324C165801399 @default.
- W4366992324 hasConceptScore W4366992324C2780186347 @default.
- W4366992324 hasConceptScore W4366992324C38652104 @default.
- W4366992324 hasConceptScore W4366992324C41008148 @default.
- W4366992324 hasConceptScore W4366992324C62520636 @default.
- W4366992324 hasConceptScore W4366992324C62649853 @default.
- W4366992324 hasConceptScore W4366992324C66322947 @default.
- W4366992324 hasConceptScore W4366992324C81363708 @default.
- W4366992324 hasFunder F4320321001 @default.
- W4366992324 hasIssue "7" @default.
- W4366992324 hasLocation W43669923241 @default.
- W4366992324 hasOpenAccess W4366992324 @default.
- W4366992324 hasPrimaryLocation W43669923241 @default.
- W4366992324 hasRelatedWork W2425127026 @default.
- W4366992324 hasRelatedWork W2731899572 @default.
- W4366992324 hasRelatedWork W2999805992 @default.
- W4366992324 hasRelatedWork W3116150086 @default.
- W4366992324 hasRelatedWork W3126336475 @default.
- W4366992324 hasRelatedWork W3133861977 @default.
- W4366992324 hasRelatedWork W4200173597 @default.
- W4366992324 hasRelatedWork W4291897433 @default.
- W4366992324 hasRelatedWork W4312417841 @default.
- W4366992324 hasRelatedWork W4321369474 @default.
- W4366992324 hasVolume "44" @default.
- W4366992324 isParatext "false" @default.
- W4366992324 isRetracted "false" @default.
- W4366992324 workType "article" @default.