FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285290151> ?p ?o ?g. }

• W4285290151 endingPage "4116" @default.
• W4285290151 startingPage "4104" @default.
• W4285290151 abstract "Extracting buildings from remote sensing images is an important task with a variety of applications. Considerable attention has focused on achieving new SOTA accuracy with more and more advanced deep learning models. However, the developed models still hardly generalize across geographical areas, hindering the practical use of SOTA approaches. To attack this problem, we established a baseline for model cross-area generalization ability using available datasets for BE. In addition to two popular FCN-based models, we first adapted two novel transformer-based models, Swin Transformer and SegFormer, which are all able to output SOTA accuracy with no big difference when tested within one area. However, experimental results show that all models fail to generalize to a different area. We then propose to fine-tune pre-trained models from one area on a small subset of an unseen area, the effectiveness of which depends on the model choice and the data size for tuning. By jointly taking advantage of the transfer learning idea and the multiscale feature learning ability of SegFormer, a distinct improvement has been achieved compared to results from Swin Transformer and FCN-based models trained on the same amount of data. Commonly used metric, IoU, can be increased from 38.97% to 70.86%, and from 48.36% to 74.51%, when using 10% and 30% subset of the targeting area, respectively. The influence of model choice and data size for tuning has also been investigated. Our work contributes to complementing the algorithm development and within-area model evaluation in the hot field of BE from RS images." @default.
• W4285290151 created "2022-07-14" @default.
• W4285290151 creator A5000359400 @default.
• W4285290151 creator A5004702834 @default.
• W4285290151 creator A5016657120 @default.
• W4285290151 creator A5042512723 @default.
• W4285290151 creator A5058601965 @default.
• W4285290151 creator A5069652653 @default.
• W4285290151 creator A5072647192 @default.
• W4285290151 date "2022-01-01" @default.
• W4285290151 modified "2023-10-13" @default.
• W4285290151 title "Transferring Transformer-Based Models for Cross-Area Building Extraction From Remote Sensing Images" @default.
• W4285290151 cites W1745334888 @default.
• W4285290151 cites W2102673432 @default.
• W4285290151 cites W2560023338 @default.
• W4285290151 cites W2563705555 @default.
• W4285290151 cites W2609402060 @default.
• W4285290151 cites W2752782242 @default.
• W4285290151 cites W2755226765 @default.
• W4285290151 cites W2804199516 @default.
• W4285290151 cites W2883423620 @default.
• W4285290151 cites W2891512280 @default.
• W4285290151 cites W2897593716 @default.
• W4285290151 cites W2897936062 @default.
• W4285290151 cites W2908320224 @default.
• W4285290151 cites W2915971115 @default.
• W4285290151 cites W2917187459 @default.
• W4285290151 cites W2938425859 @default.
• W4285290151 cites W2963881378 @default.
• W4285290151 cites W2979055326 @default.
• W4285290151 cites W2979509742 @default.
• W4285290151 cites W2982206001 @default.
• W4285290151 cites W2991441757 @default.
• W4285290151 cites W2996327453 @default.
• W4285290151 cites W3000086214 @default.
• W4285290151 cites W3015373233 @default.
• W4285290151 cites W3021057985 @default.
• W4285290151 cites W3023923911 @default.
• W4285290151 cites W3027542479 @default.
• W4285290151 cites W3034427230 @default.
• W4285290151 cites W3036045183 @default.
• W4285290151 cites W3044310826 @default.
• W4285290151 cites W3092609815 @default.
• W4285290151 cites W3105348024 @default.
• W4285290151 cites W3111390112 @default.
• W4285290151 cites W3112979587 @default.
• W4285290151 cites W3126435384 @default.
• W4285290151 cites W3129627777 @default.
• W4285290151 cites W3136393638 @default.
• W4285290151 cites W3138516171 @default.
• W4285290151 cites W3161825146 @default.
• W4285290151 cites W3170841864 @default.
• W4285290151 cites W3174867596 @default.
• W4285290151 cites W3190334976 @default.
• W4285290151 cites W3200870516 @default.
• W4285290151 cites W3202923600 @default.
• W4285290151 cites W3216720075 @default.
• W4285290151 cites W3217005392 @default.
• W4285290151 cites W3217153199 @default.
• W4285290151 cites W3217745064 @default.
• W4285290151 cites W4225773271 @default.
• W4285290151 cites W4226013274 @default.
• W4285290151 cites W4226252548 @default.
• W4285290151 cites W4288076010 @default.
• W4285290151 doi "https://doi.org/10.1109/jstars.2022.3175200" @default.
• W4285290151 hasPublicationYear "2022" @default.
• W4285290151 type Work @default.
• W4285290151 citedByCount "9" @default.
• W4285290151 countsByYear W42852901512022 @default.
• W4285290151 countsByYear W42852901512023 @default.
• W4285290151 crossrefType "journal-article" @default.
• W4285290151 hasAuthorship W4285290151A5000359400 @default.
• W4285290151 hasAuthorship W4285290151A5004702834 @default.
• W4285290151 hasAuthorship W4285290151A5016657120 @default.
• W4285290151 hasAuthorship W4285290151A5042512723 @default.
• W4285290151 hasAuthorship W4285290151A5058601965 @default.
• W4285290151 hasAuthorship W4285290151A5069652653 @default.
• W4285290151 hasAuthorship W4285290151A5072647192 @default.
• W4285290151 hasBestOaLocation W42852901511 @default.
• W4285290151 hasConcept C108583219 @default.
• W4285290151 hasConcept C119857082 @default.
• W4285290151 hasConcept C121332964 @default.
• W4285290151 hasConcept C124101348 @default.
• W4285290151 hasConcept C134306372 @default.
• W4285290151 hasConcept C150899416 @default.
• W4285290151 hasConcept C153180895 @default.
• W4285290151 hasConcept C154945302 @default.
• W4285290151 hasConcept C162324750 @default.
• W4285290151 hasConcept C165801399 @default.
• W4285290151 hasConcept C176217482 @default.
• W4285290151 hasConcept C177148314 @default.
• W4285290151 hasConcept C21547014 @default.
• W4285290151 hasConcept C33923547 @default.
• W4285290151 hasConcept C41008148 @default.
• W4285290151 hasConcept C52622490 @default.
• W4285290151 hasConcept C62520636 @default.
• W4285290151 hasConcept C66322947 @default.
• W4285290151 hasConceptScore W4285290151C108583219 @default.

• next