FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4316661208> ?p ?o ?g. }

• W4316661208 endingPage "16" @default.
• W4316661208 startingPage "1" @default.
• W4316661208 abstract "Due to more abundant data sources, more various objects of interest, and more time-consuming annotations, there is a large amount of out-of-distribution (OOD) data in the remote sensing field, on which the performance of high-accuracy image segmentation models trained under ideal experimental conditions generally degrades dramatically. Domain adaptation (DA) consequently comes into being, which aims to learn the predictor for the label-scarce target domain of interest with the help of the label-sufficient source domain in the presence of the distribution difference, namely, domain shift, between the two domains. However, the off-the-shelf DA methods for image segmentation not only struggle to cope with the more complex domain shift problems in remote sensing imagery but also almost cannot process heterogeneous data directly without information loss. While the current heterogeneous DA methods mostly still rely on some supervision information from the target domain, which is typically inaccessible in the real world. To overcome these drawbacks, we propose the multilevel heterogeneous unsupervised DA (UDA) method, termed MHDA, which unifies the instance-level DA based on cycle consistency, the feature-level DA based on contrastive learning, and the decision-level DA based on task consistency into a framework to more effectively handle the complex domain shift and heterogeneous data. After that, extensive DA experiments are conducted on the International Society for Photogrammetry and Remote Sensing (ISPRS) dataset, the BigCity dataset constructed by ourselves, and the Wuhan University (WHU) dataset, to explore the effect of each module in MHDA, the necessity of heterogeneous DA, and the effectiveness of multilevel DA. And the results demonstrate that MHDA can achieve superior performance on the remote sensing image segmentation task, compared with several state-of-the-art DA methods." @default.
• W4316661208 created "2023-01-17" @default.
• W4316661208 creator A5001960033 @default.
• W4316661208 creator A5004920623 @default.
• W4316661208 creator A5076026977 @default.
• W4316661208 creator A5076092683 @default.
• W4316661208 creator A5078148930 @default.
• W4316661208 date "2023-01-01" @default.
• W4316661208 modified "2023-10-18" @default.
• W4316661208 title "Multilevel Heterogeneous Domain Adaptation Method for Remote Sensing Image Segmentation" @default.
• W4316661208 cites W1581984155 @default.
• W4316661208 cites W1975165783 @default.
• W4316661208 cites W1978920452 @default.
• W4316661208 cites W1994348648 @default.
• W4316661208 cites W2009668020 @default.
• W4316661208 cites W2050398567 @default.
• W4316661208 cites W2062518264 @default.
• W4316661208 cites W2072128103 @default.
• W4316661208 cites W2170607218 @default.
• W4316661208 cites W2194775991 @default.
• W4316661208 cites W2422697180 @default.
• W4316661208 cites W2508804393 @default.
• W4316661208 cites W2519397578 @default.
• W4316661208 cites W2558661413 @default.
• W4316661208 cites W2788768841 @default.
• W4316661208 cites W2798681837 @default.
• W4316661208 cites W2803375486 @default.
• W4316661208 cites W2808408933 @default.
• W4316661208 cites W2886256216 @default.
• W4316661208 cites W2892946488 @default.
• W4316661208 cites W2895281799 @default.
• W4316661208 cites W2908320224 @default.
• W4316661208 cites W2955828465 @default.
• W4316661208 cites W2962793481 @default.
• W4316661208 cites W2963107255 @default.
• W4316661208 cites W2963420272 @default.
• W4316661208 cites W2963444790 @default.
• W4316661208 cites W2963789515 @default.
• W4316661208 cites W2964309882 @default.
• W4316661208 cites W2964358045 @default.
• W4316661208 cites W2979509742 @default.
• W4316661208 cites W2980096013 @default.
• W4316661208 cites W2985406498 @default.
• W4316661208 cites W3001503745 @default.
• W4316661208 cites W3005485628 @default.
• W4316661208 cites W3006326483 @default.
• W4316661208 cites W3010293082 @default.
• W4316661208 cites W3032150799 @default.
• W4316661208 cites W3034302825 @default.
• W4316661208 cites W3034373371 @default.
• W4316661208 cites W3035236545 @default.
• W4316661208 cites W3035294798 @default.
• W4316661208 cites W3035436173 @default.
• W4316661208 cites W3035524453 @default.
• W4316661208 cites W3105672835 @default.
• W4316661208 cites W3106057905 @default.
• W4316661208 cites W3157967435 @default.
• W4316661208 cites W3160132954 @default.
• W4316661208 cites W3197865432 @default.
• W4316661208 cites W4214736652 @default.
• W4316661208 cites W4285512371 @default.
• W4316661208 doi "https://doi.org/10.1109/tgrs.2023.3236957" @default.
• W4316661208 hasPublicationYear "2023" @default.
• W4316661208 type Work @default.
• W4316661208 citedByCount "0" @default.
• W4316661208 crossrefType "journal-article" @default.
• W4316661208 hasAuthorship W4316661208A5001960033 @default.
• W4316661208 hasAuthorship W4316661208A5004920623 @default.
• W4316661208 hasAuthorship W4316661208A5076026977 @default.
• W4316661208 hasAuthorship W4316661208A5076092683 @default.
• W4316661208 hasAuthorship W4316661208A5078148930 @default.
• W4316661208 hasConcept C120665830 @default.
• W4316661208 hasConcept C121332964 @default.
• W4316661208 hasConcept C124101348 @default.
• W4316661208 hasConcept C124504099 @default.
• W4316661208 hasConcept C134306372 @default.
• W4316661208 hasConcept C138885662 @default.
• W4316661208 hasConcept C139807058 @default.
• W4316661208 hasConcept C153180895 @default.
• W4316661208 hasConcept C154945302 @default.
• W4316661208 hasConcept C202444582 @default.
• W4316661208 hasConcept C205649164 @default.
• W4316661208 hasConcept C2776401178 @default.
• W4316661208 hasConcept C2776434776 @default.
• W4316661208 hasConcept C2776436953 @default.
• W4316661208 hasConcept C31972630 @default.
• W4316661208 hasConcept C33923547 @default.
• W4316661208 hasConcept C36503486 @default.
• W4316661208 hasConcept C41008148 @default.
• W4316661208 hasConcept C41895202 @default.
• W4316661208 hasConcept C62649853 @default.
• W4316661208 hasConcept C89600930 @default.
• W4316661208 hasConcept C95623464 @default.
• W4316661208 hasConcept C9652623 @default.
• W4316661208 hasConceptScore W4316661208C120665830 @default.
• W4316661208 hasConceptScore W4316661208C121332964 @default.
• W4316661208 hasConceptScore W4316661208C124101348 @default.
• W4316661208 hasConceptScore W4316661208C124504099 @default.

• next