FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4223547253> ?p ?o ?g. }

• W4223547253 endingPage "1825" @default.
• W4223547253 startingPage "1825" @default.
• W4223547253 abstract "Screening clouds, shadows, and snow is a critical pre-processing step in many remote-sensing data processing pipelines that operate on satellite image data from polar and high mountain regions. We observe that the results of the state-of-the-art Fmask algorithm are not very accurate in polar and high mountain regions. Given the unavailability of large, labeled Sentinel-2 training datasets, we present a multi-stage self-training approach that trains a model to perform semantic segmentation on Sentinel-2 L1C images using the noisy Fmask labels for training and a small human-labeled dataset for validation. At each stage of the proposed iterative framework, we use a larger network architecture in comparison to the previous stage and train a new model. The trained model at each stage is then used to generate new training labels for a bigger dataset, which are used for training the model in the next stage. We select the best model during training in each stage by evaluating the multi-class segmentation metric, mean Intersection over Union (mIoU), on the small human-labeled validation dataset. This effectively helps to correct the noisy labels. Our model achieved an overall accuracy of 93% compared to the Fmask 4 and Sen2Cor 2.8, which achieved 75% and 76%, respectively. We believe our approach can also be adapted for other remote-sensing applications for training deep-learning models with imprecise labels." @default.
• W4223547253 created "2022-04-15" @default.
• W4223547253 creator A5021805902 @default.
• W4223547253 creator A5059061090 @default.
• W4223547253 creator A5066538856 @default.
• W4223547253 creator A5077503279 @default.
• W4223547253 creator A5077777079 @default.
• W4223547253 date "2022-04-10" @default.
• W4223547253 modified "2023-10-01" @default.
• W4223547253 title "A Self-Trained Model for Cloud, Shadow and Snow Detection in Sentinel-2 Images of Snow- and Ice-Covered Regions" @default.
• W4223547253 cites W1997887332 @default.
• W4223547253 cites W2017209939 @default.
• W4223547253 cites W2022106079 @default.
• W4223547253 cites W2025745000 @default.
• W4223547253 cites W2028240797 @default.
• W4223547253 cites W2066633241 @default.
• W4223547253 cites W2109020989 @default.
• W4223547253 cites W2166251851 @default.
• W4223547253 cites W2460672227 @default.
• W4223547253 cites W2463021868 @default.
• W4223547253 cites W2517986957 @default.
• W4223547253 cites W2584156879 @default.
• W4223547253 cites W2600148249 @default.
• W4223547253 cites W2605847660 @default.
• W4223547253 cites W2734629852 @default.
• W4223547253 cites W2748715875 @default.
• W4223547253 cites W2802828972 @default.
• W4223547253 cites W2810069315 @default.
• W4223547253 cites W2908549901 @default.
• W4223547253 cites W2914757358 @default.
• W4223547253 cites W2917440533 @default.
• W4223547253 cites W2923782278 @default.
• W4223547253 cites W2946072066 @default.
• W4223547253 cites W2950314938 @default.
• W4223547253 cites W2985601188 @default.
• W4223547253 cites W3039086093 @default.
• W4223547253 cites W3080368312 @default.
• W4223547253 cites W3100944043 @default.
• W4223547253 cites W3153500217 @default.
• W4223547253 cites W3173374491 @default.
• W4223547253 cites W4206767072 @default.
• W4223547253 doi "https://doi.org/10.3390/rs14081825" @default.
• W4223547253 hasPublicationYear "2022" @default.
• W4223547253 type Work @default.
• W4223547253 citedByCount "6" @default.
• W4223547253 countsByYear W42235472532022 @default.
• W4223547253 countsByYear W42235472532023 @default.
• W4223547253 crossrefType "journal-article" @default.
• W4223547253 hasAuthorship W4223547253A5021805902 @default.
• W4223547253 hasAuthorship W4223547253A5059061090 @default.
• W4223547253 hasAuthorship W4223547253A5066538856 @default.
• W4223547253 hasAuthorship W4223547253A5077503279 @default.
• W4223547253 hasAuthorship W4223547253A5077777079 @default.
• W4223547253 hasBestOaLocation W42235472531 @default.
• W4223547253 hasConcept C108583219 @default.
• W4223547253 hasConcept C121332964 @default.
• W4223547253 hasConcept C127313418 @default.
• W4223547253 hasConcept C127413603 @default.
• W4223547253 hasConcept C146978453 @default.
• W4223547253 hasConcept C153180895 @default.
• W4223547253 hasConcept C153294291 @default.
• W4223547253 hasConcept C154945302 @default.
• W4223547253 hasConcept C200601418 @default.
• W4223547253 hasConcept C2777211547 @default.
• W4223547253 hasConcept C2780505938 @default.
• W4223547253 hasConcept C41008148 @default.
• W4223547253 hasConcept C62649853 @default.
• W4223547253 hasConcept C64543145 @default.
• W4223547253 hasConcept C89600930 @default.
• W4223547253 hasConceptScore W4223547253C108583219 @default.
• W4223547253 hasConceptScore W4223547253C121332964 @default.
• W4223547253 hasConceptScore W4223547253C127313418 @default.
• W4223547253 hasConceptScore W4223547253C127413603 @default.
• W4223547253 hasConceptScore W4223547253C146978453 @default.
• W4223547253 hasConceptScore W4223547253C153180895 @default.
• W4223547253 hasConceptScore W4223547253C153294291 @default.
• W4223547253 hasConceptScore W4223547253C154945302 @default.
• W4223547253 hasConceptScore W4223547253C200601418 @default.
• W4223547253 hasConceptScore W4223547253C2777211547 @default.
• W4223547253 hasConceptScore W4223547253C2780505938 @default.
• W4223547253 hasConceptScore W4223547253C41008148 @default.
• W4223547253 hasConceptScore W4223547253C62649853 @default.
• W4223547253 hasConceptScore W4223547253C64543145 @default.
• W4223547253 hasConceptScore W4223547253C89600930 @default.
• W4223547253 hasIssue "8" @default.
• W4223547253 hasLocation W42235472531 @default.
• W4223547253 hasLocation W42235472532 @default.
• W4223547253 hasOpenAccess W4223547253 @default.
• W4223547253 hasPrimaryLocation W42235472531 @default.
• W4223547253 hasRelatedWork W1841747458 @default.
• W4223547253 hasRelatedWork W2738221750 @default.
• W4223547253 hasRelatedWork W2790662084 @default.
• W4223547253 hasRelatedWork W2954384599 @default.
• W4223547253 hasRelatedWork W2960184797 @default.
• W4223547253 hasRelatedWork W3104734424 @default.
• W4223547253 hasRelatedWork W3134595075 @default.
• W4223547253 hasRelatedWork W3209779739 @default.
• W4223547253 hasRelatedWork W4226289457 @default.

• next