Matches in SemOpenAlex for { <https://semopenalex.org/work/W2542904986> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2542904986 abstract "We present an interactive approach to train a deep neural network pixel classifier for the segmentation of neuronal structures. An interactive training scheme reduces the extremely tedious manual annotation task that is typically required for deep networks to perform well on image segmentation problems. Our proposed method employs a feedback loop that captures sparse annotations using a graphical user interface, trains a deep neural network based on recent and past annotations, and displays the prediction output to users in almost real-time. Our implementation of the algorithm also allows multiple users to provide annotations in parallel and receive feedback from the same classifier. Quick feedback on classifier performance in an interactive setting enables users to identify and label examples that are more important than others for segmentation purposes. Our experiments show that an interactively-trained pixel classifier produces better region segmentation results on Electron Microscopy (EM) images than those generated by a network of the same architecture trained offline on exhaustive ground-truth labels." @default.
- W2542904986 created "2016-11-04" @default.
- W2542904986 creator A5003810636 @default.
- W2542904986 creator A5055757900 @default.
- W2542904986 creator A5062468877 @default.
- W2542904986 creator A5062859783 @default.
- W2542904986 creator A5069633723 @default.
- W2542904986 creator A5083779629 @default.
- W2542904986 creator A5090485738 @default.
- W2542904986 date "2017-04-01" @default.
- W2542904986 modified "2023-09-23" @default.
- W2542904986 title "ICON: An interactive approach to train deep neural networks for segmentation of neuronal structures" @default.
- W2542904986 cites W1976032673 @default.
- W2542904986 cites W2080858319 @default.
- W2542904986 cites W2121289914 @default.
- W2542904986 cites W2141273399 @default.
- W2542904986 cites W22040386 @default.
- W2542904986 cites W2232480453 @default.
- W2542904986 doi "https://doi.org/10.1109/isbi.2017.7950530" @default.
- W2542904986 hasPublicationYear "2017" @default.
- W2542904986 type Work @default.
- W2542904986 sameAs 2542904986 @default.
- W2542904986 citedByCount "8" @default.
- W2542904986 countsByYear W25429049862019 @default.
- W2542904986 countsByYear W25429049862020 @default.
- W2542904986 countsByYear W25429049862021 @default.
- W2542904986 countsByYear W25429049862022 @default.
- W2542904986 crossrefType "proceedings-article" @default.
- W2542904986 hasAuthorship W2542904986A5003810636 @default.
- W2542904986 hasAuthorship W2542904986A5055757900 @default.
- W2542904986 hasAuthorship W2542904986A5062468877 @default.
- W2542904986 hasAuthorship W2542904986A5062859783 @default.
- W2542904986 hasAuthorship W2542904986A5069633723 @default.
- W2542904986 hasAuthorship W2542904986A5083779629 @default.
- W2542904986 hasAuthorship W2542904986A5090485738 @default.
- W2542904986 hasBestOaLocation W25429049862 @default.
- W2542904986 hasConcept C108583219 @default.
- W2542904986 hasConcept C124504099 @default.
- W2542904986 hasConcept C153180895 @default.
- W2542904986 hasConcept C154945302 @default.
- W2542904986 hasConcept C160633673 @default.
- W2542904986 hasConcept C199360897 @default.
- W2542904986 hasConcept C2776321320 @default.
- W2542904986 hasConcept C31972630 @default.
- W2542904986 hasConcept C37789001 @default.
- W2542904986 hasConcept C41008148 @default.
- W2542904986 hasConcept C50644808 @default.
- W2542904986 hasConcept C89600930 @default.
- W2542904986 hasConcept C95623464 @default.
- W2542904986 hasConceptScore W2542904986C108583219 @default.
- W2542904986 hasConceptScore W2542904986C124504099 @default.
- W2542904986 hasConceptScore W2542904986C153180895 @default.
- W2542904986 hasConceptScore W2542904986C154945302 @default.
- W2542904986 hasConceptScore W2542904986C160633673 @default.
- W2542904986 hasConceptScore W2542904986C199360897 @default.
- W2542904986 hasConceptScore W2542904986C2776321320 @default.
- W2542904986 hasConceptScore W2542904986C31972630 @default.
- W2542904986 hasConceptScore W2542904986C37789001 @default.
- W2542904986 hasConceptScore W2542904986C41008148 @default.
- W2542904986 hasConceptScore W2542904986C50644808 @default.
- W2542904986 hasConceptScore W2542904986C89600930 @default.
- W2542904986 hasConceptScore W2542904986C95623464 @default.
- W2542904986 hasLocation W25429049861 @default.
- W2542904986 hasLocation W25429049862 @default.
- W2542904986 hasOpenAccess W2542904986 @default.
- W2542904986 hasPrimaryLocation W25429049861 @default.
- W2542904986 hasRelatedWork W2027450165 @default.
- W2542904986 hasRelatedWork W2124062510 @default.
- W2542904986 hasRelatedWork W2129270445 @default.
- W2542904986 hasRelatedWork W2150617545 @default.
- W2542904986 hasRelatedWork W2151600032 @default.
- W2542904986 hasRelatedWork W2507402573 @default.
- W2542904986 hasRelatedWork W2588502955 @default.
- W2542904986 hasRelatedWork W2739874619 @default.
- W2542904986 hasRelatedWork W3095523211 @default.
- W2542904986 hasRelatedWork W3103553989 @default.
- W2542904986 isParatext "false" @default.
- W2542904986 isRetracted "false" @default.
- W2542904986 magId "2542904986" @default.
- W2542904986 workType "article" @default.