Matches in SemOpenAlex for { <https://semopenalex.org/work/W3006703771> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3006703771 endingPage "647" @default.
- W3006703771 startingPage "647" @default.
- W3006703771 abstract "This study proposes a deep quadruplet network (DQN) for hyperspectral image classification given the limitation of having a small number of samples. A quadruplet network is designed, which makes use of a new quadruplet loss function in order to learn a feature space where the distances between samples from the same class are shortened, while those from a different class are enlarged. A deep 3-D convolutional neural network (CNN) with characteristics of both dense convolution and dilated convolution is then employed and embedded in the quadruplet network to extract spatial-spectral features. Finally, the nearest neighbor (NN) classifier is used to accomplish the classification in the learned feature space. The results show that the proposed network can learn a feature space and is able to undertake hyperspectral image classification using only a limited number of samples. The main highlights of the study include: (1) The proposed approach was found to have high overall accuracy and can be classified as state-of-the-art; (2) Results of the ablation study suggest that all the modules of the proposed approach are effective in improving accuracy and that the proposed quadruplet loss contributes the most; (3) Time-analysis shows the proposed methodology has a similar level of time consumption as compared with existing methods." @default.
- W3006703771 created "2020-03-06" @default.
- W3006703771 creator A5039325190 @default.
- W3006703771 creator A5042653866 @default.
- W3006703771 creator A5064831469 @default.
- W3006703771 date "2020-02-15" @default.
- W3006703771 modified "2023-10-03" @default.
- W3006703771 title "Deep Quadruplet Network for Hyperspectral Image Classification with a Small Number of Samples" @default.
- W3006703771 cites W1038672748 @default.
- W3006703771 cites W1843514792 @default.
- W3006703771 cites W1987531056 @default.
- W3006703771 cites W1990653740 @default.
- W3006703771 cites W1997718749 @default.
- W3006703771 cites W2029316659 @default.
- W3006703771 cites W2030476695 @default.
- W3006703771 cites W2081809992 @default.
- W3006703771 cites W2092745549 @default.
- W3006703771 cites W2101711129 @default.
- W3006703771 cites W2136251662 @default.
- W3006703771 cites W2314785379 @default.
- W3006703771 cites W2464755555 @default.
- W3006703771 cites W2521284359 @default.
- W3006703771 cites W2772452219 @default.
- W3006703771 cites W2800371750 @default.
- W3006703771 cites W2894165434 @default.
- W3006703771 cites W2898204262 @default.
- W3006703771 cites W2900587135 @default.
- W3006703771 cites W2901819993 @default.
- W3006703771 cites W2904478076 @default.
- W3006703771 cites W2937018631 @default.
- W3006703771 cites W2963129413 @default.
- W3006703771 cites W2963775347 @default.
- W3006703771 cites W3023114228 @default.
- W3006703771 cites W3105357426 @default.
- W3006703771 doi "https://doi.org/10.3390/rs12040647" @default.
- W3006703771 hasPublicationYear "2020" @default.
- W3006703771 type Work @default.
- W3006703771 sameAs 3006703771 @default.
- W3006703771 citedByCount "17" @default.
- W3006703771 countsByYear W30067037712020 @default.
- W3006703771 countsByYear W30067037712021 @default.
- W3006703771 countsByYear W30067037712022 @default.
- W3006703771 countsByYear W30067037712023 @default.
- W3006703771 crossrefType "journal-article" @default.
- W3006703771 hasAuthorship W3006703771A5039325190 @default.
- W3006703771 hasAuthorship W3006703771A5042653866 @default.
- W3006703771 hasAuthorship W3006703771A5064831469 @default.
- W3006703771 hasBestOaLocation W30067037711 @default.
- W3006703771 hasConcept C138885662 @default.
- W3006703771 hasConcept C153180895 @default.
- W3006703771 hasConcept C154945302 @default.
- W3006703771 hasConcept C159078339 @default.
- W3006703771 hasConcept C2776401178 @default.
- W3006703771 hasConcept C41008148 @default.
- W3006703771 hasConcept C41895202 @default.
- W3006703771 hasConcept C45347329 @default.
- W3006703771 hasConcept C50644808 @default.
- W3006703771 hasConcept C81363708 @default.
- W3006703771 hasConcept C83665646 @default.
- W3006703771 hasConcept C95623464 @default.
- W3006703771 hasConceptScore W3006703771C138885662 @default.
- W3006703771 hasConceptScore W3006703771C153180895 @default.
- W3006703771 hasConceptScore W3006703771C154945302 @default.
- W3006703771 hasConceptScore W3006703771C159078339 @default.
- W3006703771 hasConceptScore W3006703771C2776401178 @default.
- W3006703771 hasConceptScore W3006703771C41008148 @default.
- W3006703771 hasConceptScore W3006703771C41895202 @default.
- W3006703771 hasConceptScore W3006703771C45347329 @default.
- W3006703771 hasConceptScore W3006703771C50644808 @default.
- W3006703771 hasConceptScore W3006703771C81363708 @default.
- W3006703771 hasConceptScore W3006703771C83665646 @default.
- W3006703771 hasConceptScore W3006703771C95623464 @default.
- W3006703771 hasFunder F4320335595 @default.
- W3006703771 hasFunder F4320335777 @default.
- W3006703771 hasIssue "4" @default.
- W3006703771 hasLocation W30067037711 @default.
- W3006703771 hasOpenAccess W3006703771 @default.
- W3006703771 hasPrimaryLocation W30067037711 @default.
- W3006703771 hasRelatedWork W2295021132 @default.
- W3006703771 hasRelatedWork W2760085659 @default.
- W3006703771 hasRelatedWork W2929240682 @default.
- W3006703771 hasRelatedWork W2964383635 @default.
- W3006703771 hasRelatedWork W2995914718 @default.
- W3006703771 hasRelatedWork W2998169797 @default.
- W3006703771 hasRelatedWork W3106036237 @default.
- W3006703771 hasRelatedWork W3138203312 @default.
- W3006703771 hasRelatedWork W4291701050 @default.
- W3006703771 hasRelatedWork W564581980 @default.
- W3006703771 hasVolume "12" @default.
- W3006703771 isParatext "false" @default.
- W3006703771 isRetracted "false" @default.
- W3006703771 magId "3006703771" @default.
- W3006703771 workType "article" @default.