Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309402038> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4309402038 endingPage "1193" @default.
- W4309402038 startingPage "1182" @default.
- W4309402038 abstract "Convolutional Neural Network (CNN) has been proved excellent for hyperspectral image(HSI) classification on the basis of large training set. However, the lack of available samples degrades the performance of CNNs in practical HSI classification. Although transfer learning is a typical strategy to address the issue of limited training samples, such methods tend to reload source model’s feature extractors directly ignoring their generalization. Furthermore, most existing adaptive transfer learning algorithms pay attention to spectral features of HSI while the obvious difference between RGB image and HSI’s spatial features is overlooked. In this paper, the proposed method can solve the mentioned problems to some extent. Firstly, the proposed adaptive heterogeneous transfer (AHT) can measure their transferability and find appropriate solution to transfer knowledge. It computes feature extractors’ transferability based on feature maps and influences the learning process of target model through backpropagation, therefore, target model is prone to receive knowledge from feature extractors with high generalization. Secondly, the proposed method lays emphasis on HSI’s spatial features. It adopts the methodology of spatial attention and calculates the regularization loss based on spatial features. Experiments were conducted on two widely used HSI datasets. The results demonstrate the method’s effectiveness when few samples are available." @default.
- W4309402038 created "2022-11-26" @default.
- W4309402038 creator A5027034650 @default.
- W4309402038 creator A5039815946 @default.
- W4309402038 creator A5088720618 @default.
- W4309402038 date "2022-11-17" @default.
- W4309402038 modified "2023-09-24" @default.
- W4309402038 title "Adaptively heterogeneous transfer learning for hyperspectral image classification" @default.
- W4309402038 cites W2008258179 @default.
- W4309402038 cites W2500751094 @default.
- W4309402038 cites W2884585870 @default.
- W4309402038 cites W2894165434 @default.
- W4309402038 cites W2991286101 @default.
- W4309402038 cites W2998902230 @default.
- W4309402038 cites W3012405452 @default.
- W4309402038 cites W4212838577 @default.
- W4309402038 cites W4229042884 @default.
- W4309402038 doi "https://doi.org/10.1080/2150704x.2022.2133979" @default.
- W4309402038 hasPublicationYear "2022" @default.
- W4309402038 type Work @default.
- W4309402038 citedByCount "0" @default.
- W4309402038 crossrefType "journal-article" @default.
- W4309402038 hasAuthorship W4309402038A5027034650 @default.
- W4309402038 hasAuthorship W4309402038A5039815946 @default.
- W4309402038 hasAuthorship W4309402038A5088720618 @default.
- W4309402038 hasConcept C115961682 @default.
- W4309402038 hasConcept C119857082 @default.
- W4309402038 hasConcept C134306372 @default.
- W4309402038 hasConcept C138885662 @default.
- W4309402038 hasConcept C140331021 @default.
- W4309402038 hasConcept C150899416 @default.
- W4309402038 hasConcept C153180895 @default.
- W4309402038 hasConcept C154945302 @default.
- W4309402038 hasConcept C155032097 @default.
- W4309402038 hasConcept C159078339 @default.
- W4309402038 hasConcept C177148314 @default.
- W4309402038 hasConcept C2776135515 @default.
- W4309402038 hasConcept C2776401178 @default.
- W4309402038 hasConcept C33923547 @default.
- W4309402038 hasConcept C41008148 @default.
- W4309402038 hasConcept C41895202 @default.
- W4309402038 hasConcept C50644808 @default.
- W4309402038 hasConcept C61272859 @default.
- W4309402038 hasConcept C75294576 @default.
- W4309402038 hasConcept C81363708 @default.
- W4309402038 hasConcept C82990744 @default.
- W4309402038 hasConceptScore W4309402038C115961682 @default.
- W4309402038 hasConceptScore W4309402038C119857082 @default.
- W4309402038 hasConceptScore W4309402038C134306372 @default.
- W4309402038 hasConceptScore W4309402038C138885662 @default.
- W4309402038 hasConceptScore W4309402038C140331021 @default.
- W4309402038 hasConceptScore W4309402038C150899416 @default.
- W4309402038 hasConceptScore W4309402038C153180895 @default.
- W4309402038 hasConceptScore W4309402038C154945302 @default.
- W4309402038 hasConceptScore W4309402038C155032097 @default.
- W4309402038 hasConceptScore W4309402038C159078339 @default.
- W4309402038 hasConceptScore W4309402038C177148314 @default.
- W4309402038 hasConceptScore W4309402038C2776135515 @default.
- W4309402038 hasConceptScore W4309402038C2776401178 @default.
- W4309402038 hasConceptScore W4309402038C33923547 @default.
- W4309402038 hasConceptScore W4309402038C41008148 @default.
- W4309402038 hasConceptScore W4309402038C41895202 @default.
- W4309402038 hasConceptScore W4309402038C50644808 @default.
- W4309402038 hasConceptScore W4309402038C61272859 @default.
- W4309402038 hasConceptScore W4309402038C75294576 @default.
- W4309402038 hasConceptScore W4309402038C81363708 @default.
- W4309402038 hasConceptScore W4309402038C82990744 @default.
- W4309402038 hasFunder F4320321001 @default.
- W4309402038 hasIssue "12" @default.
- W4309402038 hasLocation W43094020381 @default.
- W4309402038 hasOpenAccess W4309402038 @default.
- W4309402038 hasPrimaryLocation W43094020381 @default.
- W4309402038 hasRelatedWork W2760085659 @default.
- W4309402038 hasRelatedWork W2807839383 @default.
- W4309402038 hasRelatedWork W2892483709 @default.
- W4309402038 hasRelatedWork W2940661641 @default.
- W4309402038 hasRelatedWork W3006465478 @default.
- W4309402038 hasRelatedWork W3012393889 @default.
- W4309402038 hasRelatedWork W3013138473 @default.
- W4309402038 hasRelatedWork W3153891452 @default.
- W4309402038 hasRelatedWork W3156786002 @default.
- W4309402038 hasRelatedWork W4313050734 @default.
- W4309402038 hasVolume "13" @default.
- W4309402038 isParatext "false" @default.
- W4309402038 isRetracted "false" @default.
- W4309402038 workType "article" @default.