Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286740723> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4286740723 abstract "The throughput of electron microscopes has increased significantly in recent years, enabling detailed analysis of cell morphology and ultrastructure. Analysis of neural circuits at single-synapse resolution remains the flagship target of this technique, but applications to cell and developmental biology are also starting to emerge at scale. The amount of data acquired in such studies makes manual instance segmentation, a fundamental step in many analysis pipelines, impossible. While automatic segmentation approaches have improved significantly thanks to the adoption of convolutional neural networks, their accuracy still lags behind human annotations and requires additional manual proof-reading. A major hindrance to further improvements is the limited field of view of the segmentation networks preventing them from exploiting the expected cell morphology or other prior biological knowledge which humans use to inform their segmentation decisions. In this contribution, we show how such domain-specific information can be leveraged by expressing it as long-range interactions in a graph partitioning problem known as the lifted multicut problem. Using this formulation, we demonstrate significant improvement in segmentation accuracy for three challenging EM segmentation problems from neuroscience and cell biology." @default.
- W4286740723 created "2022-07-23" @default.
- W4286740723 creator A5002688561 @default.
- W4286740723 creator A5018363483 @default.
- W4286740723 creator A5023230414 @default.
- W4286740723 creator A5034026142 @default.
- W4286740723 creator A5035594687 @default.
- W4286740723 creator A5038898203 @default.
- W4286740723 creator A5054187212 @default.
- W4286740723 creator A5062445157 @default.
- W4286740723 creator A5065148584 @default.
- W4286740723 creator A5087258300 @default.
- W4286740723 date "2019-05-25" @default.
- W4286740723 modified "2023-09-26" @default.
- W4286740723 title "Leveraging Domain Knowledge to Improve Microscopy Image Segmentation with Lifted Multicuts" @default.
- W4286740723 doi "https://doi.org/10.48550/arxiv.1905.10535" @default.
- W4286740723 hasPublicationYear "2019" @default.
- W4286740723 type Work @default.
- W4286740723 citedByCount "0" @default.
- W4286740723 crossrefType "posted-content" @default.
- W4286740723 hasAuthorship W4286740723A5002688561 @default.
- W4286740723 hasAuthorship W4286740723A5018363483 @default.
- W4286740723 hasAuthorship W4286740723A5023230414 @default.
- W4286740723 hasAuthorship W4286740723A5034026142 @default.
- W4286740723 hasAuthorship W4286740723A5035594687 @default.
- W4286740723 hasAuthorship W4286740723A5038898203 @default.
- W4286740723 hasAuthorship W4286740723A5054187212 @default.
- W4286740723 hasAuthorship W4286740723A5062445157 @default.
- W4286740723 hasAuthorship W4286740723A5065148584 @default.
- W4286740723 hasAuthorship W4286740723A5087258300 @default.
- W4286740723 hasBestOaLocation W42867407231 @default.
- W4286740723 hasConcept C119857082 @default.
- W4286740723 hasConcept C124504099 @default.
- W4286740723 hasConcept C125308379 @default.
- W4286740723 hasConcept C134306372 @default.
- W4286740723 hasConcept C144133560 @default.
- W4286740723 hasConcept C153180895 @default.
- W4286740723 hasConcept C154945302 @default.
- W4286740723 hasConcept C162853370 @default.
- W4286740723 hasConcept C169760540 @default.
- W4286740723 hasConcept C207685749 @default.
- W4286740723 hasConcept C2779097318 @default.
- W4286740723 hasConcept C3018011982 @default.
- W4286740723 hasConcept C31972630 @default.
- W4286740723 hasConcept C33923547 @default.
- W4286740723 hasConcept C36503486 @default.
- W4286740723 hasConcept C41008148 @default.
- W4286740723 hasConcept C45715564 @default.
- W4286740723 hasConcept C81363708 @default.
- W4286740723 hasConcept C86803240 @default.
- W4286740723 hasConcept C89600930 @default.
- W4286740723 hasConceptScore W4286740723C119857082 @default.
- W4286740723 hasConceptScore W4286740723C124504099 @default.
- W4286740723 hasConceptScore W4286740723C125308379 @default.
- W4286740723 hasConceptScore W4286740723C134306372 @default.
- W4286740723 hasConceptScore W4286740723C144133560 @default.
- W4286740723 hasConceptScore W4286740723C153180895 @default.
- W4286740723 hasConceptScore W4286740723C154945302 @default.
- W4286740723 hasConceptScore W4286740723C162853370 @default.
- W4286740723 hasConceptScore W4286740723C169760540 @default.
- W4286740723 hasConceptScore W4286740723C207685749 @default.
- W4286740723 hasConceptScore W4286740723C2779097318 @default.
- W4286740723 hasConceptScore W4286740723C3018011982 @default.
- W4286740723 hasConceptScore W4286740723C31972630 @default.
- W4286740723 hasConceptScore W4286740723C33923547 @default.
- W4286740723 hasConceptScore W4286740723C36503486 @default.
- W4286740723 hasConceptScore W4286740723C41008148 @default.
- W4286740723 hasConceptScore W4286740723C45715564 @default.
- W4286740723 hasConceptScore W4286740723C81363708 @default.
- W4286740723 hasConceptScore W4286740723C86803240 @default.
- W4286740723 hasConceptScore W4286740723C89600930 @default.
- W4286740723 hasLocation W42867407231 @default.
- W4286740723 hasOpenAccess W4286740723 @default.
- W4286740723 hasPrimaryLocation W42867407231 @default.
- W4286740723 hasRelatedWork W1669643531 @default.
- W4286740723 hasRelatedWork W1700740617 @default.
- W4286740723 hasRelatedWork W1721780360 @default.
- W4286740723 hasRelatedWork W2110230079 @default.
- W4286740723 hasRelatedWork W2117664411 @default.
- W4286740723 hasRelatedWork W2117933325 @default.
- W4286740723 hasRelatedWork W2122581818 @default.
- W4286740723 hasRelatedWork W2159066190 @default.
- W4286740723 hasRelatedWork W2739874619 @default.
- W4286740723 hasRelatedWork W2979932740 @default.
- W4286740723 isParatext "false" @default.
- W4286740723 isRetracted "false" @default.
- W4286740723 workType "article" @default.