Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989738275> ?p ?o ?g. }
- W2989738275 endingPage "2515" @default.
- W2989738275 startingPage "2504" @default.
- W2989738275 abstract "Cross-domain scene classification refers to the scene classification task in which the training set (termed source domain) and the test set (termed target domain) come from different distributions. Various domain adaptation methods have been developed to reduce the distribution discrepancy between different domains. However, current domain adaptation methods assume that the source domain and target domain share the same categories. In reality, it is hard to find a source domain that can completely cover all the categories of target domain. In this article, we propose to use multiple complementary source domains to form the categories of target domain. A multisource compensation network (MSCN) is proposed to tackle these challenges: distribution discrepancy and category incompleteness. First, a pretrained convolutional neural network (CNN) is exploited to learn the feature representation for each domain. Second, a cross-domain alignment module is developed to reduce the domain shift between source and target domains. Domain shift is reduced by mapping the two domain features into a common feature space. Finally, a classifier complement module is proposed to align categories in multiple sources and learn a target classifier. Two cross-domain classification data sets are constructed using four heterogeneous remote sensing scene classification data sets. Extensive experiments are conducted on these datasets to validate the effectiveness of the proposed method. The proposed method can achieve 81.23% and 81.97% average accuracies on two-source-complementary data set and three-source-complementary data set, respectively." @default.
- W2989738275 created "2019-12-05" @default.
- W2989738275 creator A5007883693 @default.
- W2989738275 creator A5018824735 @default.
- W2989738275 creator A5065068394 @default.
- W2989738275 date "2020-04-01" @default.
- W2989738275 modified "2023-10-17" @default.
- W2989738275 title "Multisource Compensation Network for Remote Sensing Cross-Domain Scene Classification" @default.
- W2989738275 cites W1912954554 @default.
- W2989738275 cites W1978920452 @default.
- W2989738275 cites W1980038761 @default.
- W2989738275 cites W2064447488 @default.
- W2989738275 cites W2098676252 @default.
- W2989738275 cites W2108598243 @default.
- W2989738275 cites W2115403315 @default.
- W2989738275 cites W2214409633 @default.
- W2989738275 cites W2253590344 @default.
- W2989738275 cites W2320738207 @default.
- W2989738275 cites W2551868040 @default.
- W2989738275 cites W2583503935 @default.
- W2989738275 cites W2593768305 @default.
- W2989738275 cites W2610614780 @default.
- W2989738275 cites W2614424296 @default.
- W2989738275 cites W2620858446 @default.
- W2989738275 cites W2621526417 @default.
- W2989738275 cites W2626107033 @default.
- W2989738275 cites W2779610669 @default.
- W2989738275 cites W2783165089 @default.
- W2989738275 cites W2792088634 @default.
- W2989738275 cites W2793797551 @default.
- W2989738275 cites W2798964604 @default.
- W2989738275 cites W2890732922 @default.
- W2989738275 cites W2897086142 @default.
- W2989738275 cites W2899885135 @default.
- W2989738275 cites W2903122811 @default.
- W2989738275 cites W2903882179 @default.
- W2989738275 cites W2909431441 @default.
- W2989738275 cites W2911305027 @default.
- W2989738275 cites W2911584214 @default.
- W2989738275 cites W2917187459 @default.
- W2989738275 cites W2963118547 @default.
- W2989738275 cites W2963506806 @default.
- W2989738275 cites W3103856189 @default.
- W2989738275 cites W3105577662 @default.
- W2989738275 doi "https://doi.org/10.1109/tgrs.2019.2951779" @default.
- W2989738275 hasPublicationYear "2020" @default.
- W2989738275 type Work @default.
- W2989738275 sameAs 2989738275 @default.
- W2989738275 citedByCount "70" @default.
- W2989738275 countsByYear W29897382752020 @default.
- W2989738275 countsByYear W29897382752021 @default.
- W2989738275 countsByYear W29897382752022 @default.
- W2989738275 countsByYear W29897382752023 @default.
- W2989738275 crossrefType "journal-article" @default.
- W2989738275 hasAuthorship W2989738275A5007883693 @default.
- W2989738275 hasAuthorship W2989738275A5018824735 @default.
- W2989738275 hasAuthorship W2989738275A5065068394 @default.
- W2989738275 hasConcept C11171543 @default.
- W2989738275 hasConcept C127313418 @default.
- W2989738275 hasConcept C134306372 @default.
- W2989738275 hasConcept C153180895 @default.
- W2989738275 hasConcept C154945302 @default.
- W2989738275 hasConcept C15744967 @default.
- W2989738275 hasConcept C2780023022 @default.
- W2989738275 hasConcept C31972630 @default.
- W2989738275 hasConcept C33923547 @default.
- W2989738275 hasConcept C36503486 @default.
- W2989738275 hasConcept C41008148 @default.
- W2989738275 hasConcept C62649853 @default.
- W2989738275 hasConceptScore W2989738275C11171543 @default.
- W2989738275 hasConceptScore W2989738275C127313418 @default.
- W2989738275 hasConceptScore W2989738275C134306372 @default.
- W2989738275 hasConceptScore W2989738275C153180895 @default.
- W2989738275 hasConceptScore W2989738275C154945302 @default.
- W2989738275 hasConceptScore W2989738275C15744967 @default.
- W2989738275 hasConceptScore W2989738275C2780023022 @default.
- W2989738275 hasConceptScore W2989738275C31972630 @default.
- W2989738275 hasConceptScore W2989738275C33923547 @default.
- W2989738275 hasConceptScore W2989738275C36503486 @default.
- W2989738275 hasConceptScore W2989738275C41008148 @default.
- W2989738275 hasConceptScore W2989738275C62649853 @default.
- W2989738275 hasFunder F4320321001 @default.
- W2989738275 hasFunder F4320321133 @default.
- W2989738275 hasFunder F4320335777 @default.
- W2989738275 hasIssue "4" @default.
- W2989738275 hasLocation W29897382751 @default.
- W2989738275 hasOpenAccess W2989738275 @default.
- W2989738275 hasPrimaryLocation W29897382751 @default.
- W2989738275 hasRelatedWork W1891287906 @default.
- W2989738275 hasRelatedWork W1969923398 @default.
- W2989738275 hasRelatedWork W2036807459 @default.
- W2989738275 hasRelatedWork W2058170566 @default.
- W2989738275 hasRelatedWork W2065134433 @default.
- W2989738275 hasRelatedWork W2229312674 @default.
- W2989738275 hasRelatedWork W2755342338 @default.
- W2989738275 hasRelatedWork W2772917594 @default.
- W2989738275 hasRelatedWork W2967493046 @default.
- W2989738275 hasRelatedWork W3116076068 @default.