Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285060170> ?p ?o ?g. }
- W4285060170 endingPage "15" @default.
- W4285060170 startingPage "1" @default.
- W4285060170 abstract "With the continuous progress of computer deep learning technology, convolutional neural network (CNN), as a representative approach, provides a unique solution for hyperspectral image (HSI) classification. However, the parameters of CNN can not be well-tuned when the number of training samples is insufficient, resulting in unsatisfactory classification performance. To tackle the thorny problem, a deep ensemble CNN method based on sample expansion for HSI classification is studied in this paper. Specially, spatial information is first extracted and fused with original spectral bands to help classifiers obtain discriminant spectral-spatial features. Then we use the pixel-pair feature (PPF) to expand the number of training samples so that the parameters of CNN structure can be fully trained. In addition, deep ensemble CNN is employed in this paper, enabling the trained model to obtain better generalization ability and more robust classification results. Ultimately, the proposed method is applied to classify four widely used hyperspectral data sets. Experimental results show that the studied approach yields higher classification accuracy than some CNN-based methods even under the condition of small-size training set." @default.
- W4285060170 created "2022-07-13" @default.
- W4285060170 creator A5008256662 @default.
- W4285060170 creator A5021408538 @default.
- W4285060170 creator A5028522401 @default.
- W4285060170 creator A5044570096 @default.
- W4285060170 creator A5066378186 @default.
- W4285060170 creator A5068336830 @default.
- W4285060170 date "2022-01-01" @default.
- W4285060170 modified "2023-10-15" @default.
- W4285060170 title "Deep Ensemble CNN Method Based on Sample Expansion for Hyperspectral Image Classification" @default.
- W4285060170 cites W1521436688 @default.
- W4285060170 cites W1563375353 @default.
- W4285060170 cites W1966580635 @default.
- W4285060170 cites W1976507318 @default.
- W4285060170 cites W1994830145 @default.
- W4285060170 cites W2036195817 @default.
- W4285060170 cites W2044465660 @default.
- W4285060170 cites W2104269704 @default.
- W4285060170 cites W2169500530 @default.
- W4285060170 cites W2212636544 @default.
- W4285060170 cites W2309693750 @default.
- W4285060170 cites W2316226477 @default.
- W4285060170 cites W2544832372 @default.
- W4285060170 cites W2548791488 @default.
- W4285060170 cites W2555840851 @default.
- W4285060170 cites W2563755014 @default.
- W4285060170 cites W2617818785 @default.
- W4285060170 cites W2757242159 @default.
- W4285060170 cites W2768537477 @default.
- W4285060170 cites W2784118841 @default.
- W4285060170 cites W2805177060 @default.
- W4285060170 cites W2943270518 @default.
- W4285060170 cites W2945989246 @default.
- W4285060170 cites W2946655868 @default.
- W4285060170 cites W2954914461 @default.
- W4285060170 cites W2977002487 @default.
- W4285060170 cites W2984140474 @default.
- W4285060170 cites W2987422477 @default.
- W4285060170 cites W2991286101 @default.
- W4285060170 cites W2994639710 @default.
- W4285060170 cites W2997343747 @default.
- W4285060170 cites W2999529768 @default.
- W4285060170 cites W3023736619 @default.
- W4285060170 cites W3031015423 @default.
- W4285060170 cites W3031696400 @default.
- W4285060170 cites W3037490781 @default.
- W4285060170 cites W3039712633 @default.
- W4285060170 cites W3047443805 @default.
- W4285060170 cites W3089256253 @default.
- W4285060170 cites W3093600558 @default.
- W4285060170 cites W3100714546 @default.
- W4285060170 cites W3101012758 @default.
- W4285060170 cites W3104795559 @default.
- W4285060170 cites W3115148830 @default.
- W4285060170 cites W3128776197 @default.
- W4285060170 cites W3130652158 @default.
- W4285060170 cites W3131722669 @default.
- W4285060170 cites W3140801455 @default.
- W4285060170 cites W3141129286 @default.
- W4285060170 cites W3148263657 @default.
- W4285060170 cites W3171569697 @default.
- W4285060170 cites W3174597340 @default.
- W4285060170 cites W3205406278 @default.
- W4285060170 cites W3206592002 @default.
- W4285060170 cites W3209733456 @default.
- W4285060170 cites W4225575963 @default.
- W4285060170 doi "https://doi.org/10.1109/tgrs.2022.3183189" @default.
- W4285060170 hasPublicationYear "2022" @default.
- W4285060170 type Work @default.
- W4285060170 citedByCount "5" @default.
- W4285060170 countsByYear W42850601702022 @default.
- W4285060170 countsByYear W42850601702023 @default.
- W4285060170 crossrefType "journal-article" @default.
- W4285060170 hasAuthorship W4285060170A5008256662 @default.
- W4285060170 hasAuthorship W4285060170A5021408538 @default.
- W4285060170 hasAuthorship W4285060170A5028522401 @default.
- W4285060170 hasAuthorship W4285060170A5044570096 @default.
- W4285060170 hasAuthorship W4285060170A5066378186 @default.
- W4285060170 hasAuthorship W4285060170A5068336830 @default.
- W4285060170 hasConcept C108583219 @default.
- W4285060170 hasConcept C115961682 @default.
- W4285060170 hasConcept C134306372 @default.
- W4285060170 hasConcept C138885662 @default.
- W4285060170 hasConcept C153180895 @default.
- W4285060170 hasConcept C154945302 @default.
- W4285060170 hasConcept C159078339 @default.
- W4285060170 hasConcept C160633673 @default.
- W4285060170 hasConcept C177148314 @default.
- W4285060170 hasConcept C185592680 @default.
- W4285060170 hasConcept C198531522 @default.
- W4285060170 hasConcept C2776401178 @default.
- W4285060170 hasConcept C33923547 @default.
- W4285060170 hasConcept C41008148 @default.
- W4285060170 hasConcept C41895202 @default.
- W4285060170 hasConcept C43617362 @default.
- W4285060170 hasConcept C45942800 @default.
- W4285060170 hasConcept C52622490 @default.