Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891798045> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2891798045 endingPage "91" @default.
- W2891798045 startingPage "83" @default.
- W2891798045 abstract "Deep learning with convolutional neural networks (CNN) has achieved unprecedented success in segmentation, however it requires large training data, which is expensive to obtain. Active Learning (AL) frameworks can facilitate major improvements in CNN performance with intelligent selection of minimal data to be labeled. This paper proposes a novel diversified AL based on Fisher information (FI) for the first time for CNNs, where gradient computations from backpropagation are used for efficient computation of FI on the large CNN parameter space. We evaluated the proposed method in the context of newborn and adolescent brain extraction problem under two scenarios: (1) semi-automatic segmentation of a particular subject from a different age group or with a pathology not available in the original training data, where starting from an inaccurate pre-trained model, we iteratively label small number of voxels queried by AL until the model generates accurate segmentation for that subject, and (2) using AL to build a universal model generalizable to all images in a given data set. In both scenarios, FI-based AL improved performance after labeling a small percentage (less than 0.05%) of voxels. The results showed that FI-based AL significantly outperformed random sampling, and achieved accuracy higher than entropy-based querying in transfer learning, where the model learns to extract brains of newborn subjects given an initial model trained on adolescents." @default.
- W2891798045 created "2018-09-27" @default.
- W2891798045 creator A5029980254 @default.
- W2891798045 creator A5042038501 @default.
- W2891798045 creator A5054913205 @default.
- W2891798045 creator A5058812679 @default.
- W2891798045 creator A5078857532 @default.
- W2891798045 date "2018-01-01" @default.
- W2891798045 modified "2023-09-27" @default.
- W2891798045 title "Active Deep Learning with Fisher Information for Patch-Wise Semantic Segmentation" @default.
- W2891798045 cites W1683159118 @default.
- W2891798045 cites W2104848109 @default.
- W2891798045 cites W2266059378 @default.
- W2891798045 cites W2471138382 @default.
- W2891798045 cites W2592929672 @default.
- W2891798045 cites W2625559849 @default.
- W2891798045 cites W2748386424 @default.
- W2891798045 cites W2912522929 @default.
- W2891798045 cites W2953130519 @default.
- W2891798045 doi "https://doi.org/10.1007/978-3-030-00889-5_10" @default.
- W2891798045 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6235453" @default.
- W2891798045 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30450490" @default.
- W2891798045 hasPublicationYear "2018" @default.
- W2891798045 type Work @default.
- W2891798045 sameAs 2891798045 @default.
- W2891798045 citedByCount "20" @default.
- W2891798045 countsByYear W28917980452019 @default.
- W2891798045 countsByYear W28917980452020 @default.
- W2891798045 countsByYear W28917980452021 @default.
- W2891798045 countsByYear W28917980452022 @default.
- W2891798045 countsByYear W28917980452023 @default.
- W2891798045 crossrefType "book-chapter" @default.
- W2891798045 hasAuthorship W2891798045A5029980254 @default.
- W2891798045 hasAuthorship W2891798045A5042038501 @default.
- W2891798045 hasAuthorship W2891798045A5054913205 @default.
- W2891798045 hasAuthorship W2891798045A5058812679 @default.
- W2891798045 hasAuthorship W2891798045A5078857532 @default.
- W2891798045 hasBestOaLocation W28917980452 @default.
- W2891798045 hasConcept C108583219 @default.
- W2891798045 hasConcept C119857082 @default.
- W2891798045 hasConcept C151730666 @default.
- W2891798045 hasConcept C153180895 @default.
- W2891798045 hasConcept C154945302 @default.
- W2891798045 hasConcept C2779343474 @default.
- W2891798045 hasConcept C41008148 @default.
- W2891798045 hasConcept C54170458 @default.
- W2891798045 hasConcept C81363708 @default.
- W2891798045 hasConcept C86803240 @default.
- W2891798045 hasConcept C89600930 @default.
- W2891798045 hasConceptScore W2891798045C108583219 @default.
- W2891798045 hasConceptScore W2891798045C119857082 @default.
- W2891798045 hasConceptScore W2891798045C151730666 @default.
- W2891798045 hasConceptScore W2891798045C153180895 @default.
- W2891798045 hasConceptScore W2891798045C154945302 @default.
- W2891798045 hasConceptScore W2891798045C2779343474 @default.
- W2891798045 hasConceptScore W2891798045C41008148 @default.
- W2891798045 hasConceptScore W2891798045C54170458 @default.
- W2891798045 hasConceptScore W2891798045C81363708 @default.
- W2891798045 hasConceptScore W2891798045C86803240 @default.
- W2891798045 hasConceptScore W2891798045C89600930 @default.
- W2891798045 hasLocation W28917980451 @default.
- W2891798045 hasLocation W28917980452 @default.
- W2891798045 hasLocation W28917980453 @default.
- W2891798045 hasLocation W28917980454 @default.
- W2891798045 hasOpenAccess W2891798045 @default.
- W2891798045 hasPrimaryLocation W28917980451 @default.
- W2891798045 hasRelatedWork W2731899572 @default.
- W2891798045 hasRelatedWork W2790662084 @default.
- W2891798045 hasRelatedWork W2999805992 @default.
- W2891798045 hasRelatedWork W3116150086 @default.
- W2891798045 hasRelatedWork W3133861977 @default.
- W2891798045 hasRelatedWork W4200173597 @default.
- W2891798045 hasRelatedWork W4291897433 @default.
- W2891798045 hasRelatedWork W4312417841 @default.
- W2891798045 hasRelatedWork W4321369474 @default.
- W2891798045 hasRelatedWork W4380075502 @default.
- W2891798045 isParatext "false" @default.
- W2891798045 isRetracted "false" @default.
- W2891798045 magId "2891798045" @default.
- W2891798045 workType "book-chapter" @default.