FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208539124> ?p ?o ?g. }

• W3208539124 endingPage "4194" @default.
• W3208539124 startingPage "4194" @default.
• W3208539124 abstract "Large-scale land-cover classification using a supervised algorithm is a challenging task. Enormous efforts have been made to manually process and check the production of national land-cover maps. This has led to complex pre- and post-processing and even the production of inaccurate mapping products from large-scale remote sensing images. Inspired by the recent success of deep learning techniques, in this study we provided a feasible automatic solution for improving the quality of national land-cover maps. However, the application of deep learning to national land-cover mapping remains limited because only small-scale noisy labels are available. To this end, a mutual transfer network MTNet was developed. MTNet is capable of learning better feature representations by mutually transferring pre-trained models from time-series of data and fine-tuning current data. An interactive training strategy such as this can effectively alleviate the effects of inaccurate or noisy labels and unbalanced sample distributions, thus yielding a relatively stable classification system. Extensive experiments were conducted by focusing on several representative regions to evaluate the classification results of our proposed method. Quantitative results showed that the proposed MTNet outperformed its baseline model about 1%, and the accuracy can be improved up to 6.45% compared with the model trained by the training set of another year. We also visualized the national classification maps generated by MTNet for two different time periods to quantitatively analyze the performance gain. It was concluded that the proposed MTNet provides an efficient method for large-scale land cover mapping." @default.
• W3208539124 created "2021-11-08" @default.
• W3208539124 creator A5010054986 @default.
• W3208539124 creator A5035508615 @default.
• W3208539124 creator A5045473616 @default.
• W3208539124 creator A5066378186 @default.
• W3208539124 creator A5075013625 @default.
• W3208539124 date "2021-10-20" @default.
• W3208539124 modified "2023-10-09" @default.
• W3208539124 title "Transferable Deep Learning from Time Series of Landsat Data for National Land-Cover Mapping with Noisy Labels: A Case Study of China" @default.
• W3208539124 cites W1514928307 @default.
• W3208539124 cites W1554190159 @default.
• W3208539124 cites W1996777760 @default.
• W3208539124 cites W2001510610 @default.
• W3208539124 cites W2006929658 @default.
• W3208539124 cites W2020127479 @default.
• W3208539124 cites W2063907334 @default.
• W3208539124 cites W2137900926 @default.
• W3208539124 cites W2170804038 @default.
• W3208539124 cites W2248723555 @default.
• W3208539124 cites W2261059368 @default.
• W3208539124 cites W2334867485 @default.
• W3208539124 cites W2344186514 @default.
• W3208539124 cites W2395611524 @default.
• W3208539124 cites W2590695810 @default.
• W3208539124 cites W2618530766 @default.
• W3208539124 cites W2648242067 @default.
• W3208539124 cites W2740144340 @default.
• W3208539124 cites W2793461576 @default.
• W3208539124 cites W2803946774 @default.
• W3208539124 cites W2811244448 @default.
• W3208539124 cites W2890022946 @default.
• W3208539124 cites W2899101283 @default.
• W3208539124 cites W2903980171 @default.
• W3208539124 cites W2911964244 @default.
• W3208539124 cites W2920254659 @default.
• W3208539124 cites W2922063907 @default.
• W3208539124 cites W2939520333 @default.
• W3208539124 cites W2942497932 @default.
• W3208539124 cites W2943838191 @default.
• W3208539124 cites W2952946204 @default.
• W3208539124 cites W2955716942 @default.
• W3208539124 cites W2993182755 @default.
• W3208539124 cites W2996060033 @default.
• W3208539124 cites W2997150065 @default.
• W3208539124 cites W2997444859 @default.
• W3208539124 cites W2999209063 @default.
• W3208539124 cites W3032150799 @default.
• W3208539124 cites W3040988483 @default.
• W3208539124 cites W3041664846 @default.
• W3208539124 cites W3047443805 @default.
• W3208539124 cites W3048631361 @default.
• W3208539124 cites W3090449663 @default.
• W3208539124 cites W3100714546 @default.
• W3208539124 cites W3101012758 @default.
• W3208539124 cites W3107349585 @default.
• W3208539124 cites W3145674614 @default.
• W3208539124 cites W3154887629 @default.
• W3208539124 cites W3160553908 @default.
• W3208539124 cites W3168367808 @default.
• W3208539124 cites W3172754087 @default.
• W3208539124 cites W3202921355 @default.
• W3208539124 cites W4236137412 @default.
• W3208539124 cites W4239944110 @default.
• W3208539124 cites W4248710273 @default.
• W3208539124 doi "https://doi.org/10.3390/rs13214194" @default.
• W3208539124 hasPublicationYear "2021" @default.
• W3208539124 type Work @default.
• W3208539124 sameAs 3208539124 @default.
• W3208539124 citedByCount "4" @default.
• W3208539124 countsByYear W32085391242022 @default.
• W3208539124 countsByYear W32085391242023 @default.
• W3208539124 crossrefType "journal-article" @default.
• W3208539124 hasAuthorship W3208539124A5010054986 @default.
• W3208539124 hasAuthorship W3208539124A5035508615 @default.
• W3208539124 hasAuthorship W3208539124A5045473616 @default.
• W3208539124 hasAuthorship W3208539124A5066378186 @default.
• W3208539124 hasAuthorship W3208539124A5075013625 @default.
• W3208539124 hasBestOaLocation W32085391241 @default.
• W3208539124 hasConcept C111368507 @default.
• W3208539124 hasConcept C111919701 @default.
• W3208539124 hasConcept C119857082 @default.
• W3208539124 hasConcept C124101348 @default.
• W3208539124 hasConcept C12725497 @default.
• W3208539124 hasConcept C127313418 @default.
• W3208539124 hasConcept C127413603 @default.
• W3208539124 hasConcept C138885662 @default.
• W3208539124 hasConcept C147176958 @default.
• W3208539124 hasConcept C150899416 @default.
• W3208539124 hasConcept C153180895 @default.
• W3208539124 hasConcept C154945302 @default.
• W3208539124 hasConcept C205649164 @default.
• W3208539124 hasConcept C2776401178 @default.
• W3208539124 hasConcept C2778755073 @default.
• W3208539124 hasConcept C2780428219 @default.
• W3208539124 hasConcept C2780648208 @default.
• W3208539124 hasConcept C41008148 @default.
• W3208539124 hasConcept C41895202 @default.

• next