Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042302007> ?p ?o ?g. }
- W3042302007 endingPage "308" @default.
- W3042302007 startingPage "297" @default.
- W3042302007 abstract "An efficient strategy for weakly-supervised segmentation is to impose constraints or regularization priors on target regions. Recent efforts have focused on incorporating such constraints in the training of convolutional neural networks (CNN), however this has so far been done within a continuous optimization framework. Yet, various segmentation constraints and regularization priors can be modeled and optimized more efficiently in a discrete formulation. This paper proposes a method, based on the alternating direction method of multipliers (ADMM) algorithm, to train a CNN with discrete constraints and regularization priors. This method is applied to the segmentation of medical images with weak annotations, where both size constraints and boundary length regularization are enforced. Experiments on two benchmark datasets for medical image segmentation show our method to provide significant improvements compared to existing approaches in terms of segmentation accuracy, constraint satisfaction and convergence speed." @default.
- W3042302007 created "2020-07-23" @default.
- W3042302007 creator A5004770604 @default.
- W3042302007 creator A5017608284 @default.
- W3042302007 creator A5039660800 @default.
- W3042302007 creator A5053292735 @default.
- W3042302007 creator A5053557557 @default.
- W3042302007 creator A5057382610 @default.
- W3042302007 date "2020-10-01" @default.
- W3042302007 modified "2023-10-16" @default.
- W3042302007 title "Discretely-constrained deep network for weakly supervised segmentation" @default.
- W3042302007 cites W1495267108 @default.
- W3042302007 cites W1586409345 @default.
- W3042302007 cites W1783315696 @default.
- W3042302007 cites W2015429465 @default.
- W3042302007 cites W2106033751 @default.
- W3042302007 cites W2114855512 @default.
- W3042302007 cites W2143516773 @default.
- W3042302007 cites W2337429362 @default.
- W3042302007 cites W2396622801 @default.
- W3042302007 cites W2567599812 @default.
- W3042302007 cites W2591100698 @default.
- W3042302007 cites W2592929672 @default.
- W3042302007 cites W2601686579 @default.
- W3042302007 cites W2607363228 @default.
- W3042302007 cites W2608100259 @default.
- W3042302007 cites W2770223833 @default.
- W3042302007 cites W2771375885 @default.
- W3042302007 cites W2799738340 @default.
- W3042302007 cites W2804047627 @default.
- W3042302007 cites W2896184058 @default.
- W3042302007 cites W2903320160 @default.
- W3042302007 cites W2913909435 @default.
- W3042302007 cites W2982430624 @default.
- W3042302007 cites W3106105822 @default.
- W3042302007 cites W4292363360 @default.
- W3042302007 doi "https://doi.org/10.1016/j.neunet.2020.07.011" @default.
- W3042302007 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32721843" @default.
- W3042302007 hasPublicationYear "2020" @default.
- W3042302007 type Work @default.
- W3042302007 sameAs 3042302007 @default.
- W3042302007 citedByCount "27" @default.
- W3042302007 countsByYear W30423020072020 @default.
- W3042302007 countsByYear W30423020072021 @default.
- W3042302007 countsByYear W30423020072022 @default.
- W3042302007 countsByYear W30423020072023 @default.
- W3042302007 crossrefType "journal-article" @default.
- W3042302007 hasAuthorship W3042302007A5004770604 @default.
- W3042302007 hasAuthorship W3042302007A5017608284 @default.
- W3042302007 hasAuthorship W3042302007A5039660800 @default.
- W3042302007 hasAuthorship W3042302007A5053292735 @default.
- W3042302007 hasAuthorship W3042302007A5053557557 @default.
- W3042302007 hasAuthorship W3042302007A5057382610 @default.
- W3042302007 hasBestOaLocation W30423020072 @default.
- W3042302007 hasConcept C107673813 @default.
- W3042302007 hasConcept C108583219 @default.
- W3042302007 hasConcept C11413529 @default.
- W3042302007 hasConcept C124504099 @default.
- W3042302007 hasConcept C126255220 @default.
- W3042302007 hasConcept C153180895 @default.
- W3042302007 hasConcept C154945302 @default.
- W3042302007 hasConcept C177769412 @default.
- W3042302007 hasConcept C2776135515 @default.
- W3042302007 hasConcept C33923547 @default.
- W3042302007 hasConcept C41008148 @default.
- W3042302007 hasConcept C81363708 @default.
- W3042302007 hasConcept C89600930 @default.
- W3042302007 hasConceptScore W3042302007C107673813 @default.
- W3042302007 hasConceptScore W3042302007C108583219 @default.
- W3042302007 hasConceptScore W3042302007C11413529 @default.
- W3042302007 hasConceptScore W3042302007C124504099 @default.
- W3042302007 hasConceptScore W3042302007C126255220 @default.
- W3042302007 hasConceptScore W3042302007C153180895 @default.
- W3042302007 hasConceptScore W3042302007C154945302 @default.
- W3042302007 hasConceptScore W3042302007C177769412 @default.
- W3042302007 hasConceptScore W3042302007C2776135515 @default.
- W3042302007 hasConceptScore W3042302007C33923547 @default.
- W3042302007 hasConceptScore W3042302007C41008148 @default.
- W3042302007 hasConceptScore W3042302007C81363708 @default.
- W3042302007 hasConceptScore W3042302007C89600930 @default.
- W3042302007 hasFunder F4320321487 @default.
- W3042302007 hasLocation W30423020071 @default.
- W3042302007 hasLocation W30423020072 @default.
- W3042302007 hasLocation W30423020073 @default.
- W3042302007 hasOpenAccess W3042302007 @default.
- W3042302007 hasPrimaryLocation W30423020071 @default.
- W3042302007 hasRelatedWork W2731899572 @default.
- W3042302007 hasRelatedWork W2790662084 @default.
- W3042302007 hasRelatedWork W2960184797 @default.
- W3042302007 hasRelatedWork W2999805992 @default.
- W3042302007 hasRelatedWork W3116150086 @default.
- W3042302007 hasRelatedWork W3133861977 @default.
- W3042302007 hasRelatedWork W4200173597 @default.
- W3042302007 hasRelatedWork W4285827401 @default.
- W3042302007 hasRelatedWork W4312417841 @default.
- W3042302007 hasRelatedWork W4321369474 @default.
- W3042302007 hasVolume "130" @default.
- W3042302007 isParatext "false" @default.