FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200420711> ?p ?o ?g. }

• W3200420711 endingPage "128" @default.
• W3200420711 startingPage "113" @default.
• W3200420711 abstract "Changes in environmental conditions, geographical variability and different sensor properties typically make it almost impossible to employ previously trained classifiers for new data without a significant drop in classification accuracy. Domain adaptation (DA) techniques been proven useful to alleviate that problem. In particular, appearance adaptation techniques may be used to adapt images from a specific dataset in such a way that the generated images have a style that is similar to the images from another dataset. Such techniques are, however, prone to creating artifacts that hinder proper classification of the adapted images. In this work we propose an unsupervised DA approach for change detection tasks, which is based on a particular appearance adaptation method: the Cycle-Consistent Generative Adversarial Network (CycleGAN). Specifically, we extend that method by introducing additional constraints in the training phase of the model components, which make it preserve the semantic structure and class transitions in the adapted images. We evaluate the proposed approach on a deforestation detection application, considering different sites in the Amazon rain-forest and in the Brazilian Cerrado (savanna) using Landsat-8 images. In the experiments, each site corresponds to a domain, and the accuracy of a classifier trained with images and references from one (source) domain is measured in the classification of another (target) domain. The results show that the proposed approach is successful in producing artifact-free adapted images, which can be satisfactory classified by the pre-trained source classifiers. On average, the accuracies achieved in the classification of the adapted images outperformed the baselines (when no adaptation was made) by 7.1% in terms of mean average precision, and 9.1% in terms of F1-Score. To the best of our knowledge, the proposed method is the first unsupervised domain adaptation approach devised for change detection." @default.
• W3200420711 created "2021-09-27" @default.
• W3200420711 creator A5033807047 @default.
• W3200420711 creator A5038352101 @default.
• W3200420711 creator A5045645901 @default.
• W3200420711 creator A5046173075 @default.
• W3200420711 creator A5067983564 @default.
• W3200420711 creator A5069418475 @default.
• W3200420711 creator A5074026543 @default.
• W3200420711 date "2021-11-01" @default.
• W3200420711 modified "2023-10-18" @default.
• W3200420711 title "An unsupervised domain adaptation approach for change detection and its application to deforestation mapping in tropical biomes" @default.
• W3200420711 cites W1901129140 @default.
• W3200420711 cites W1967711432 @default.
• W3200420711 cites W1973445088 @default.
• W3200420711 cites W1974234045 @default.
• W3200420711 cites W2001536813 @default.
• W3200420711 cites W2022416612 @default.
• W3200420711 cites W2084892946 @default.
• W3200420711 cites W2085283969 @default.
• W3200420711 cites W2085487226 @default.
• W3200420711 cites W2090590748 @default.
• W3200420711 cites W2098676252 @default.
• W3200420711 cites W2134969826 @default.
• W3200420711 cites W2146444479 @default.
• W3200420711 cites W2149665650 @default.
• W3200420711 cites W2157100165 @default.
• W3200420711 cites W2160544350 @default.
• W3200420711 cites W2165698076 @default.
• W3200420711 cites W2294798173 @default.
• W3200420711 cites W2312255383 @default.
• W3200420711 cites W2343614411 @default.
• W3200420711 cites W2395579298 @default.
• W3200420711 cites W2564935578 @default.
• W3200420711 cites W2724081917 @default.
• W3200420711 cites W2782522152 @default.
• W3200420711 cites W2786808285 @default.
• W3200420711 cites W2917187459 @default.
• W3200420711 cites W2918202904 @default.
• W3200420711 cites W2919115771 @default.
• W3200420711 cites W2921442714 @default.
• W3200420711 cites W2964288524 @default.
• W3200420711 cites W2973483023 @default.
• W3200420711 cites W3003384866 @default.
• W3200420711 cites W3011869042 @default.
• W3200420711 cites W3080079534 @default.
• W3200420711 cites W3080321256 @default.
• W3200420711 cites W3080805846 @default.
• W3200420711 cites W3105672835 @default.
• W3200420711 cites W3196212409 @default.
• W3200420711 cites W4288076010 @default.
• W3200420711 doi "https://doi.org/10.1016/j.isprsjprs.2021.08.026" @default.
• W3200420711 hasPublicationYear "2021" @default.
• W3200420711 type Work @default.
• W3200420711 sameAs 3200420711 @default.
• W3200420711 citedByCount "14" @default.
• W3200420711 countsByYear W32004207112022 @default.
• W3200420711 countsByYear W32004207112023 @default.
• W3200420711 crossrefType "journal-article" @default.
• W3200420711 hasAuthorship W3200420711A5033807047 @default.
• W3200420711 hasAuthorship W3200420711A5038352101 @default.
• W3200420711 hasAuthorship W3200420711A5045645901 @default.
• W3200420711 hasAuthorship W3200420711A5046173075 @default.
• W3200420711 hasAuthorship W3200420711A5067983564 @default.
• W3200420711 hasAuthorship W3200420711A5069418475 @default.
• W3200420711 hasAuthorship W3200420711A5074026543 @default.
• W3200420711 hasConcept C115961682 @default.
• W3200420711 hasConcept C119857082 @default.
• W3200420711 hasConcept C120665830 @default.
• W3200420711 hasConcept C121332964 @default.
• W3200420711 hasConcept C134306372 @default.
• W3200420711 hasConcept C139807058 @default.
• W3200420711 hasConcept C153180895 @default.
• W3200420711 hasConcept C154945302 @default.
• W3200420711 hasConcept C169258074 @default.
• W3200420711 hasConcept C203595873 @default.
• W3200420711 hasConcept C2776434776 @default.
• W3200420711 hasConcept C33923547 @default.
• W3200420711 hasConcept C36503486 @default.
• W3200420711 hasConcept C41008148 @default.
• W3200420711 hasConcept C75294576 @default.
• W3200420711 hasConcept C95623464 @default.
• W3200420711 hasConceptScore W3200420711C115961682 @default.
• W3200420711 hasConceptScore W3200420711C119857082 @default.
• W3200420711 hasConceptScore W3200420711C120665830 @default.
• W3200420711 hasConceptScore W3200420711C121332964 @default.
• W3200420711 hasConceptScore W3200420711C134306372 @default.
• W3200420711 hasConceptScore W3200420711C139807058 @default.
• W3200420711 hasConceptScore W3200420711C153180895 @default.
• W3200420711 hasConceptScore W3200420711C154945302 @default.
• W3200420711 hasConceptScore W3200420711C169258074 @default.
• W3200420711 hasConceptScore W3200420711C203595873 @default.
• W3200420711 hasConceptScore W3200420711C2776434776 @default.
• W3200420711 hasConceptScore W3200420711C33923547 @default.
• W3200420711 hasConceptScore W3200420711C36503486 @default.
• W3200420711 hasConceptScore W3200420711C41008148 @default.
• W3200420711 hasConceptScore W3200420711C75294576 @default.
• W3200420711 hasConceptScore W3200420711C95623464 @default.

• next