Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292964483> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4292964483 endingPage "5" @default.
- W4292964483 startingPage "1" @default.
- W4292964483 abstract "Image segmentation is a challenging and essential task in remote sensing. Deep neural networks (DNNs) have successfully segmented images from different domains, but the models usually require time-consuming and expensive pixel-level data annotation. In this letter, we exploit a recent technique to learn features (an encoder) from a few markers placed by the user in relevant image regions, build an encoder–decoder model from a small set of regions delineated by click-based segmentation, and use that model to annotate the remaining pixels. Such user-guided data expansion modeling can be repeated as the encoder–decoder network improves, and by selecting well-annotated regions, the user considerably expands the pixel set to train DNNs with little supervision. We show the role of feature learning from image markers (FLIM) and that our data expansion model can significantly improve the generalization performance of a state-of-the-art DNN when segmenting buildings in aerial images of distinct cities." @default.
- W4292964483 created "2022-08-24" @default.
- W4292964483 creator A5003819002 @default.
- W4292964483 creator A5015267493 @default.
- W4292964483 creator A5020661409 @default.
- W4292964483 creator A5027303526 @default.
- W4292964483 creator A5049489283 @default.
- W4292964483 date "2022-01-01" @default.
- W4292964483 modified "2023-10-01" @default.
- W4292964483 title "User-Guided Data Expansion Modeling to Train Deep Neural Networks With Little Supervision" @default.
- W4292964483 doi "https://doi.org/10.1109/lgrs.2022.3201437" @default.
- W4292964483 hasPublicationYear "2022" @default.
- W4292964483 type Work @default.
- W4292964483 citedByCount "0" @default.
- W4292964483 crossrefType "journal-article" @default.
- W4292964483 hasAuthorship W4292964483A5003819002 @default.
- W4292964483 hasAuthorship W4292964483A5015267493 @default.
- W4292964483 hasAuthorship W4292964483A5020661409 @default.
- W4292964483 hasAuthorship W4292964483A5027303526 @default.
- W4292964483 hasAuthorship W4292964483A5049489283 @default.
- W4292964483 hasConcept C154945302 @default.
- W4292964483 hasConcept C41008148 @default.
- W4292964483 hasConcept C50644808 @default.
- W4292964483 hasConcept C67186912 @default.
- W4292964483 hasConcept C77088390 @default.
- W4292964483 hasConceptScore W4292964483C154945302 @default.
- W4292964483 hasConceptScore W4292964483C41008148 @default.
- W4292964483 hasConceptScore W4292964483C50644808 @default.
- W4292964483 hasConceptScore W4292964483C67186912 @default.
- W4292964483 hasConceptScore W4292964483C77088390 @default.
- W4292964483 hasFunder F4320320997 @default.
- W4292964483 hasFunder F4320322025 @default.
- W4292964483 hasFunder F4320322468 @default.
- W4292964483 hasFunder F4320323909 @default.
- W4292964483 hasLocation W42929644831 @default.
- W4292964483 hasOpenAccess W4292964483 @default.
- W4292964483 hasPrimaryLocation W42929644831 @default.
- W4292964483 hasRelatedWork W1525948649 @default.
- W4292964483 hasRelatedWork W1793019783 @default.
- W4292964483 hasRelatedWork W1990368964 @default.
- W4292964483 hasRelatedWork W2097917438 @default.
- W4292964483 hasRelatedWork W2159443810 @default.
- W4292964483 hasRelatedWork W2223752138 @default.
- W4292964483 hasRelatedWork W2386387936 @default.
- W4292964483 hasRelatedWork W644753246 @default.
- W4292964483 hasRelatedWork W89695409 @default.
- W4292964483 hasRelatedWork W1629725936 @default.
- W4292964483 hasVolume "19" @default.
- W4292964483 isParatext "false" @default.
- W4292964483 isRetracted "false" @default.
- W4292964483 workType "article" @default.