Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201748440> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3201748440 endingPage "3836" @default.
- W3201748440 startingPage "3836" @default.
- W3201748440 abstract "In recent years, numerous deep learning techniques have been proposed to tackle the semantic segmentation of aerial and satellite images, increase trust in the leaderboards of main scientific contests and represent the current state-of-the-art. Nevertheless, despite their promising results, these state-of-the-art techniques are still unable to provide results with the level of accuracy sought in real applications, i.e., in operational settings. Thus, it is mandatory to qualify these segmentation results and estimate the uncertainty brought about by a deep network. In this work, we address uncertainty estimations in semantic segmentation. To do this, we relied on a Bayesian deep learning method, based on Monte Carlo Dropout, which allows us to derive uncertainty metrics along with the semantic segmentation. Built on the most widespread U-Net architecture, our model achieves semantic segmentation with high accuracy on several state-of-the-art datasets. More importantly, uncertainty maps are also derived from our model. While they allow for the performance of a sounder qualitative evaluation of the segmentation results, they also include valuable information to improve the reference databases." @default.
- W3201748440 created "2021-10-11" @default.
- W3201748440 creator A5007397898 @default.
- W3201748440 creator A5024171000 @default.
- W3201748440 creator A5076433052 @default.
- W3201748440 date "2021-09-25" @default.
- W3201748440 modified "2023-09-30" @default.
- W3201748440 title "Bayesian U-Net: Estimating Uncertainty in Semantic Segmentation of Earth Observation Images" @default.
- W3201748440 cites W2102673432 @default.
- W3201748440 cites W2171943915 @default.
- W3201748440 cites W2412782625 @default.
- W3201748440 cites W2469938794 @default.
- W3201748440 cites W2760340275 @default.
- W3201748440 cites W2919115771 @default.
- W3201748440 cites W2945528352 @default.
- W3201748440 cites W2963659230 @default.
- W3201748440 cites W2963881378 @default.
- W3201748440 cites W3007268491 @default.
- W3201748440 cites W3103557498 @default.
- W3201748440 cites W3138136606 @default.
- W3201748440 cites W3153261712 @default.
- W3201748440 cites W3174867596 @default.
- W3201748440 doi "https://doi.org/10.3390/rs13193836" @default.
- W3201748440 hasPublicationYear "2021" @default.
- W3201748440 type Work @default.
- W3201748440 sameAs 3201748440 @default.
- W3201748440 citedByCount "15" @default.
- W3201748440 countsByYear W32017484402021 @default.
- W3201748440 countsByYear W32017484402022 @default.
- W3201748440 countsByYear W32017484402023 @default.
- W3201748440 crossrefType "journal-article" @default.
- W3201748440 hasAuthorship W3201748440A5007397898 @default.
- W3201748440 hasAuthorship W3201748440A5024171000 @default.
- W3201748440 hasAuthorship W3201748440A5076433052 @default.
- W3201748440 hasBestOaLocation W32017484401 @default.
- W3201748440 hasConcept C107673813 @default.
- W3201748440 hasConcept C108583219 @default.
- W3201748440 hasConcept C119857082 @default.
- W3201748440 hasConcept C124101348 @default.
- W3201748440 hasConcept C154945302 @default.
- W3201748440 hasConcept C160234255 @default.
- W3201748440 hasConcept C184337299 @default.
- W3201748440 hasConcept C199360897 @default.
- W3201748440 hasConcept C2776145597 @default.
- W3201748440 hasConcept C32230216 @default.
- W3201748440 hasConcept C33724603 @default.
- W3201748440 hasConcept C41008148 @default.
- W3201748440 hasConcept C89600930 @default.
- W3201748440 hasConceptScore W3201748440C107673813 @default.
- W3201748440 hasConceptScore W3201748440C108583219 @default.
- W3201748440 hasConceptScore W3201748440C119857082 @default.
- W3201748440 hasConceptScore W3201748440C124101348 @default.
- W3201748440 hasConceptScore W3201748440C154945302 @default.
- W3201748440 hasConceptScore W3201748440C160234255 @default.
- W3201748440 hasConceptScore W3201748440C184337299 @default.
- W3201748440 hasConceptScore W3201748440C199360897 @default.
- W3201748440 hasConceptScore W3201748440C2776145597 @default.
- W3201748440 hasConceptScore W3201748440C32230216 @default.
- W3201748440 hasConceptScore W3201748440C33724603 @default.
- W3201748440 hasConceptScore W3201748440C41008148 @default.
- W3201748440 hasConceptScore W3201748440C89600930 @default.
- W3201748440 hasIssue "19" @default.
- W3201748440 hasLocation W32017484401 @default.
- W3201748440 hasLocation W32017484402 @default.
- W3201748440 hasLocation W32017484403 @default.
- W3201748440 hasLocation W32017484404 @default.
- W3201748440 hasLocation W32017484405 @default.
- W3201748440 hasOpenAccess W3201748440 @default.
- W3201748440 hasPrimaryLocation W32017484401 @default.
- W3201748440 hasRelatedWork W2790662084 @default.
- W3201748440 hasRelatedWork W3014300295 @default.
- W3201748440 hasRelatedWork W4223943233 @default.
- W3201748440 hasRelatedWork W4225161397 @default.
- W3201748440 hasRelatedWork W4309045103 @default.
- W3201748440 hasRelatedWork W4312200629 @default.
- W3201748440 hasRelatedWork W4360585206 @default.
- W3201748440 hasRelatedWork W4364306694 @default.
- W3201748440 hasRelatedWork W4380075502 @default.
- W3201748440 hasRelatedWork W4380086463 @default.
- W3201748440 hasVolume "13" @default.
- W3201748440 isParatext "false" @default.
- W3201748440 isRetracted "false" @default.
- W3201748440 magId "3201748440" @default.
- W3201748440 workType "article" @default.