Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226338172> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4226338172 abstract "Despite recent advances in deep-learning based semantic segmentation, automatic building detection from remotely sensed imagery is still a challenging problem owing to large variability in the appearance of buildings across the globe. The errors occur mostly around the boundaries of the building footprints, in shadow areas, and when detecting buildings whose exterior surfaces have reflectivity properties that are very similar to those of the surrounding regions. To overcome these problems, we propose a generative adversarial network based segmentation framework with uncertainty attention unit and refinement module embedded in the generator. The refinement module, composed of edge and reverse attention units, is designed to refine the predicted building map. The edge attention enhances the boundary features to estimate building boundaries with greater precision, and the reverse attention allows the network to explore the features missing in the previously estimated regions. The uncertainty attention unit assists the network in resolving uncertainties in classification. As a measure of the power of our approach, as of December 4, 2021, it ranks at the second place on DeepGlobe's public leaderboard despite the fact that main focus of our approach -- refinement of the building edges -- does not align exactly with the metrics used for leaderboard rankings. Our overall F1-score on DeepGlobe's challenging dataset is 0.745. We also report improvements on the previous-best results for the challenging INRIA Validation Dataset for which our network achieves an overall IoU of 81.28% and an overall accuracy of 97.03%. Along the same lines, for the official INRIA Test Dataset, our network scores 77.86% and 96.41% in overall IoU and accuracy." @default.
- W4226338172 created "2022-05-05" @default.
- W4226338172 creator A5009123726 @default.
- W4226338172 creator A5084427797 @default.
- W4226338172 date "2021-12-09" @default.
- W4226338172 modified "2023-09-27" @default.
- W4226338172 title "Uncertainty, Edge, and Reverse-Attention Guided Generative Adversarial Network for Automatic Building Detection in Remotely Sensed Images" @default.
- W4226338172 hasPublicationYear "2021" @default.
- W4226338172 type Work @default.
- W4226338172 citedByCount "0" @default.
- W4226338172 crossrefType "posted-content" @default.
- W4226338172 hasAuthorship W4226338172A5009123726 @default.
- W4226338172 hasAuthorship W4226338172A5084427797 @default.
- W4226338172 hasBestOaLocation W42263381721 @default.
- W4226338172 hasConcept C108583219 @default.
- W4226338172 hasConcept C117797892 @default.
- W4226338172 hasConcept C119857082 @default.
- W4226338172 hasConcept C120665830 @default.
- W4226338172 hasConcept C121332964 @default.
- W4226338172 hasConcept C124101348 @default.
- W4226338172 hasConcept C134306372 @default.
- W4226338172 hasConcept C153180895 @default.
- W4226338172 hasConcept C154945302 @default.
- W4226338172 hasConcept C15744967 @default.
- W4226338172 hasConcept C162307627 @default.
- W4226338172 hasConcept C163258240 @default.
- W4226338172 hasConcept C166957645 @default.
- W4226338172 hasConcept C192209626 @default.
- W4226338172 hasConcept C205649164 @default.
- W4226338172 hasConcept C2780009758 @default.
- W4226338172 hasConcept C2780113678 @default.
- W4226338172 hasConcept C2780992000 @default.
- W4226338172 hasConcept C33923547 @default.
- W4226338172 hasConcept C41008148 @default.
- W4226338172 hasConcept C542102704 @default.
- W4226338172 hasConcept C62354387 @default.
- W4226338172 hasConcept C62520636 @default.
- W4226338172 hasConcept C89600930 @default.
- W4226338172 hasConceptScore W4226338172C108583219 @default.
- W4226338172 hasConceptScore W4226338172C117797892 @default.
- W4226338172 hasConceptScore W4226338172C119857082 @default.
- W4226338172 hasConceptScore W4226338172C120665830 @default.
- W4226338172 hasConceptScore W4226338172C121332964 @default.
- W4226338172 hasConceptScore W4226338172C124101348 @default.
- W4226338172 hasConceptScore W4226338172C134306372 @default.
- W4226338172 hasConceptScore W4226338172C153180895 @default.
- W4226338172 hasConceptScore W4226338172C154945302 @default.
- W4226338172 hasConceptScore W4226338172C15744967 @default.
- W4226338172 hasConceptScore W4226338172C162307627 @default.
- W4226338172 hasConceptScore W4226338172C163258240 @default.
- W4226338172 hasConceptScore W4226338172C166957645 @default.
- W4226338172 hasConceptScore W4226338172C192209626 @default.
- W4226338172 hasConceptScore W4226338172C205649164 @default.
- W4226338172 hasConceptScore W4226338172C2780009758 @default.
- W4226338172 hasConceptScore W4226338172C2780113678 @default.
- W4226338172 hasConceptScore W4226338172C2780992000 @default.
- W4226338172 hasConceptScore W4226338172C33923547 @default.
- W4226338172 hasConceptScore W4226338172C41008148 @default.
- W4226338172 hasConceptScore W4226338172C542102704 @default.
- W4226338172 hasConceptScore W4226338172C62354387 @default.
- W4226338172 hasConceptScore W4226338172C62520636 @default.
- W4226338172 hasConceptScore W4226338172C89600930 @default.
- W4226338172 hasLocation W42263381721 @default.
- W4226338172 hasOpenAccess W4226338172 @default.
- W4226338172 hasPrimaryLocation W42263381721 @default.
- W4226338172 hasRelatedWork W1000462 @default.
- W4226338172 hasRelatedWork W1105034 @default.
- W4226338172 hasRelatedWork W12718294 @default.
- W4226338172 hasRelatedWork W1446482 @default.
- W4226338172 hasRelatedWork W15123885 @default.
- W4226338172 hasRelatedWork W15292189 @default.
- W4226338172 hasRelatedWork W1679810 @default.
- W4226338172 hasRelatedWork W1865761 @default.
- W4226338172 hasRelatedWork W2893967 @default.
- W4226338172 hasRelatedWork W6572092 @default.
- W4226338172 isParatext "false" @default.
- W4226338172 isRetracted "false" @default.
- W4226338172 workType "article" @default.