FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366331277> ?p ?o ?g. }

• W4366331277 endingPage "4138" @default.
• W4366331277 startingPage "4122" @default.
• W4366331277 abstract "In this paper, we introduce a new building dataset and propose a novel domain generalization method to facilitate the development of building extraction from high-resolution remote sensing images. The problem with the current building datasets involves that they lack diversity to train a practical learning model with good generalization ability, and the quality of the labels is unsatisfactory. To address these issues, we built a diverse, large-scale, and high-quality building dataset named the WHU-Mix building dataset, which is more practice-oriented. The WHU-Mix building dataset consists of a training/validation set containing 43,727 diverse images collected from all over the world, and a test set containing 8402 images from five other cities on five continents. In addition, to further improve the generalization ability of a building extraction model, we propose a domain generalization method named batch style mixing (BSM), which can be embedded as an efficient plug-and-play module in the front-end of a building extraction model, providing the model with a progressively larger data distribution to learn data-invariant knowledge. The experiments conducted in this study confirmed the potential of the WHU-Mix building dataset to improve the performance of a building extraction model, resulting in a 6–36% improvement in mIoU, compared to the other existing datasets. The adverse impact of the inaccurate labels in the other datasets can cause about 20% IoU decrease. The experiments also confirmed the high performance of the proposed BSM module in enhancing the generalization ability and robustness of a model, exceeding the baseline model without domain generalization by 13% and the recent domain generalization methods by 4–15% in mIoU." @default.
• W4366331277 created "2023-04-20" @default.
• W4366331277 creator A5031588692 @default.
• W4366331277 creator A5039630821 @default.
• W4366331277 creator A5083320689 @default.
• W4366331277 date "2023-01-01" @default.
• W4366331277 modified "2023-09-26" @default.
• W4366331277 title "A Diverse Large-Scale Building Dataset and a Novel Plug-and-Play Domain Generalization Method for Building Extraction" @default.
• W4366331277 cites W2019038438 @default.
• W4366331277 cites W2066004332 @default.
• W4366331277 cites W2097117768 @default.
• W4366331277 cites W2108598243 @default.
• W4366331277 cites W2194775991 @default.
• W4366331277 cites W2340897893 @default.
• W4366331277 cites W2346746376 @default.
• W4366331277 cites W2583638424 @default.
• W4366331277 cites W2603777577 @default.
• W4366331277 cites W2609402060 @default.
• W4366331277 cites W2798658180 @default.
• W4366331277 cites W2908320224 @default.
• W4366331277 cites W2954896312 @default.
• W4366331277 cites W2955058313 @default.
• W4366331277 cites W2958360136 @default.
• W4366331277 cites W2962793481 @default.
• W4366331277 cites W2963043696 @default.
• W4366331277 cites W2963275094 @default.
• W4366331277 cites W2963625477 @default.
• W4366331277 cites W2981429991 @default.
• W4366331277 cites W2981540341 @default.
• W4366331277 cites W2982204955 @default.
• W4366331277 cites W2987385519 @default.
• W4366331277 cites W2992240579 @default.
• W4366331277 cites W2996327453 @default.
• W4366331277 cites W2997195386 @default.
• W4366331277 cites W2998653622 @default.
• W4366331277 cites W2999187804 @default.
• W4366331277 cites W3016198642 @default.
• W4366331277 cites W3028207073 @default.
• W4366331277 cites W3034727830 @default.
• W4366331277 cites W3035236545 @default.
• W4366331277 cites W3035294798 @default.
• W4366331277 cites W3091842132 @default.
• W4366331277 cites W3100521496 @default.
• W4366331277 cites W3122259118 @default.
• W4366331277 cites W3137744231 @default.
• W4366331277 cites W3148283428 @default.
• W4366331277 cites W3162767959 @default.
• W4366331277 cites W3169545167 @default.
• W4366331277 cites W3186981108 @default.
• W4366331277 cites W3196212409 @default.
• W4366331277 cites W3198011468 @default.
• W4366331277 cites W4213172700 @default.
• W4366331277 cites W4214914649 @default.
• W4366331277 cites W4285725586 @default.
• W4366331277 cites W4288076010 @default.
• W4366331277 doi "https://doi.org/10.1109/jstars.2023.3268176" @default.
• W4366331277 hasPublicationYear "2023" @default.
• W4366331277 type Work @default.
• W4366331277 citedByCount "1" @default.
• W4366331277 countsByYear W43663312772023 @default.
• W4366331277 crossrefType "journal-article" @default.
• W4366331277 hasAuthorship W4366331277A5031588692 @default.
• W4366331277 hasAuthorship W4366331277A5039630821 @default.
• W4366331277 hasAuthorship W4366331277A5083320689 @default.
• W4366331277 hasBestOaLocation W43663312771 @default.
• W4366331277 hasConcept C104317684 @default.
• W4366331277 hasConcept C119857082 @default.
• W4366331277 hasConcept C121332964 @default.
• W4366331277 hasConcept C124101348 @default.
• W4366331277 hasConcept C134306372 @default.
• W4366331277 hasConcept C154945302 @default.
• W4366331277 hasConcept C169903167 @default.
• W4366331277 hasConcept C177148314 @default.
• W4366331277 hasConcept C177264268 @default.
• W4366331277 hasConcept C185592680 @default.
• W4366331277 hasConcept C189474733 @default.
• W4366331277 hasConcept C199360897 @default.
• W4366331277 hasConcept C2778755073 @default.
• W4366331277 hasConcept C33923547 @default.
• W4366331277 hasConcept C36503486 @default.
• W4366331277 hasConcept C41008148 @default.
• W4366331277 hasConcept C55493867 @default.
• W4366331277 hasConcept C62520636 @default.
• W4366331277 hasConcept C63479239 @default.
• W4366331277 hasConceptScore W4366331277C104317684 @default.
• W4366331277 hasConceptScore W4366331277C119857082 @default.
• W4366331277 hasConceptScore W4366331277C121332964 @default.
• W4366331277 hasConceptScore W4366331277C124101348 @default.
• W4366331277 hasConceptScore W4366331277C134306372 @default.
• W4366331277 hasConceptScore W4366331277C154945302 @default.
• W4366331277 hasConceptScore W4366331277C169903167 @default.
• W4366331277 hasConceptScore W4366331277C177148314 @default.
• W4366331277 hasConceptScore W4366331277C177264268 @default.
• W4366331277 hasConceptScore W4366331277C185592680 @default.
• W4366331277 hasConceptScore W4366331277C189474733 @default.
• W4366331277 hasConceptScore W4366331277C199360897 @default.
• W4366331277 hasConceptScore W4366331277C2778755073 @default.
• W4366331277 hasConceptScore W4366331277C33923547 @default.

• next