Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284963977> ?p ?o ?g. }
- W4284963977 endingPage "6781" @default.
- W4284963977 startingPage "6765" @default.
- W4284963977 abstract "Representing features at multiple scales is of great significance for hyperspectral image classification. However, the most existing methods improve the feature representation ability by extracting features with different resolutions. Moreover, the existing attention methods have not taken full advantage of the HSI data, and their receptive field sizes of artificial neurons in each layer are identical, while in neuroscience, the receptive field sizes of visual cortical neurons adapt to the neural stimulation. Therefore, in this paper, we propose a Res2Net with spectral-spatial and channel attention (SSCAR2N) for hyperspectral image classification. To effectively extract multi-scale features of HSI image at a more granular level while ensuring a small amount of calculation and low parameter redundancy, the Res2Net block is adopted. To further recalibrate the features from spectral, spatial and channel dimensions simultaneously, we propose a visual threefold (spectral, spatial and channel) attention mechanism, where a dynamic neuron selection mechanism that allows each neuron to adaptively adjust the size of its receptive fields based on the multiple scales of the input information is designed. The comparison experiments on three benchmark hyperspectral image data sets demonstrate that the proposed SSCAR2N outperforms several state-of-the-art deep learning based HSI classification methods." @default.
- W4284963977 created "2022-07-10" @default.
- W4284963977 creator A5002309775 @default.
- W4284963977 creator A5005697228 @default.
- W4284963977 creator A5015415784 @default.
- W4284963977 creator A5016004424 @default.
- W4284963977 creator A5017694550 @default.
- W4284963977 creator A5081006499 @default.
- W4284963977 date "2022-09-22" @default.
- W4284963977 modified "2023-09-27" @default.
- W4284963977 title "Res2Net with spectral-spatial and channel attention for hyperspectral image classification" @default.
- W4284963977 cites W1950365613 @default.
- W4284963977 cites W1968258303 @default.
- W4284963977 cites W1971891445 @default.
- W4284963977 cites W1998691552 @default.
- W4284963977 cites W2029316659 @default.
- W4284963977 cites W2073827457 @default.
- W4284963977 cites W2097092275 @default.
- W4284963977 cites W2101711129 @default.
- W4284963977 cites W2131864940 @default.
- W4284963977 cites W2136251662 @default.
- W4284963977 cites W2164437025 @default.
- W4284963977 cites W2345118402 @default.
- W4284963977 cites W2500751094 @default.
- W4284963977 cites W2572303978 @default.
- W4284963977 cites W2603422184 @default.
- W4284963977 cites W2611655888 @default.
- W4284963977 cites W2626498975 @default.
- W4284963977 cites W2764276316 @default.
- W4284963977 cites W2772452219 @default.
- W4284963977 cites W2791006446 @default.
- W4284963977 cites W2892075618 @default.
- W4284963977 cites W2907100627 @default.
- W4284963977 cites W2908955282 @default.
- W4284963977 cites W2928165649 @default.
- W4284963977 cites W2966751049 @default.
- W4284963977 cites W2987110818 @default.
- W4284963977 cites W2989871747 @default.
- W4284963977 cites W2991616716 @default.
- W4284963977 cites W3022951770 @default.
- W4284963977 cites W3031696400 @default.
- W4284963977 cites W3043181422 @default.
- W4284963977 cites W3047317383 @default.
- W4284963977 cites W3082700671 @default.
- W4284963977 cites W3114720220 @default.
- W4284963977 cites W3123061203 @default.
- W4284963977 cites W4213358987 @default.
- W4284963977 cites W4240485910 @default.
- W4284963977 doi "https://doi.org/10.3233/jifs-220863" @default.
- W4284963977 hasPublicationYear "2022" @default.
- W4284963977 type Work @default.
- W4284963977 citedByCount "0" @default.
- W4284963977 crossrefType "journal-article" @default.
- W4284963977 hasAuthorship W4284963977A5002309775 @default.
- W4284963977 hasAuthorship W4284963977A5005697228 @default.
- W4284963977 hasAuthorship W4284963977A5015415784 @default.
- W4284963977 hasAuthorship W4284963977A5016004424 @default.
- W4284963977 hasAuthorship W4284963977A5017694550 @default.
- W4284963977 hasAuthorship W4284963977A5081006499 @default.
- W4284963977 hasConcept C105795698 @default.
- W4284963977 hasConcept C111919701 @default.
- W4284963977 hasConcept C127162648 @default.
- W4284963977 hasConcept C13280743 @default.
- W4284963977 hasConcept C152124472 @default.
- W4284963977 hasConcept C153180895 @default.
- W4284963977 hasConcept C154945302 @default.
- W4284963977 hasConcept C159078339 @default.
- W4284963977 hasConcept C159620131 @default.
- W4284963977 hasConcept C185798385 @default.
- W4284963977 hasConcept C19071747 @default.
- W4284963977 hasConcept C205649164 @default.
- W4284963977 hasConcept C2524010 @default.
- W4284963977 hasConcept C2777210771 @default.
- W4284963977 hasConcept C31258907 @default.
- W4284963977 hasConcept C31972630 @default.
- W4284963977 hasConcept C33923547 @default.
- W4284963977 hasConcept C41008148 @default.
- W4284963977 hasConceptScore W4284963977C105795698 @default.
- W4284963977 hasConceptScore W4284963977C111919701 @default.
- W4284963977 hasConceptScore W4284963977C127162648 @default.
- W4284963977 hasConceptScore W4284963977C13280743 @default.
- W4284963977 hasConceptScore W4284963977C152124472 @default.
- W4284963977 hasConceptScore W4284963977C153180895 @default.
- W4284963977 hasConceptScore W4284963977C154945302 @default.
- W4284963977 hasConceptScore W4284963977C159078339 @default.
- W4284963977 hasConceptScore W4284963977C159620131 @default.
- W4284963977 hasConceptScore W4284963977C185798385 @default.
- W4284963977 hasConceptScore W4284963977C19071747 @default.
- W4284963977 hasConceptScore W4284963977C205649164 @default.
- W4284963977 hasConceptScore W4284963977C2524010 @default.
- W4284963977 hasConceptScore W4284963977C2777210771 @default.
- W4284963977 hasConceptScore W4284963977C31258907 @default.
- W4284963977 hasConceptScore W4284963977C31972630 @default.
- W4284963977 hasConceptScore W4284963977C33923547 @default.
- W4284963977 hasConceptScore W4284963977C41008148 @default.
- W4284963977 hasIssue "5" @default.
- W4284963977 hasLocation W42849639771 @default.
- W4284963977 hasOpenAccess W4284963977 @default.