Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204221214> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W3204221214 endingPage "460" @default.
- W3204221214 startingPage "450" @default.
- W3204221214 abstract "Due to the difficulty in accessing a large amount of labeled data, semi-supervised learning is becoming an attractive solution in medical image segmentation. To make use of unlabeled data, current popular semi-supervised methods (e.g., temporal ensembling, mean teacher) mainly impose data-level and model-level consistency on unlabeled data. In this paper, we argue that in addition to these strategies, we could further utilize auxiliary tasks and consider task-level consistency to better leverage unlabeled data for segmentation. Specifically, we introduce two auxiliary tasks, i.e., a foreground and background reconstruction task for capturing semantic information and a signed distance field (SDF) prediction task for imposing shape constraint, and explore the mutual promotion effect between the two auxiliary and the segmentation tasks based on mean teacher architecture. Moreover, to handle the potential bias of the teacher model caused by annotation scarcity, we develop a tripled-uncertainty guided framework to encourage the three tasks in the teacher model to generate more reliable pseudo labels. When calculating uncertainty, we propose an uncertainty weighted integration (UWI) strategy for yielding the segmentation predictions of the teacher. Extensive experiments on public 2017 ACDC dataset and PROMISE12 dataset have demostrated the effectiveness of our method. Code is available at https://github.com/DeepMedLab/Tri-U-MT." @default.
- W3204221214 created "2021-10-11" @default.
- W3204221214 creator A5003642180 @default.
- W3204221214 creator A5009301235 @default.
- W3204221214 creator A5021875517 @default.
- W3204221214 creator A5030763508 @default.
- W3204221214 creator A5041675502 @default.
- W3204221214 creator A5072543841 @default.
- W3204221214 creator A5089126739 @default.
- W3204221214 date "2021-01-01" @default.
- W3204221214 modified "2023-10-17" @default.
- W3204221214 title "Tripled-Uncertainty Guided Mean Teacher Model for Semi-supervised Medical Image Segmentation" @default.
- W3204221214 cites W1901129140 @default.
- W3204221214 cites W2106033751 @default.
- W3204221214 cites W2804047627 @default.
- W3204221214 cites W2962914239 @default.
- W3204221214 cites W2979433110 @default.
- W3204221214 cites W2979632994 @default.
- W3204221214 cites W2979651795 @default.
- W3204221214 cites W2979907638 @default.
- W3204221214 cites W2998663558 @default.
- W3204221214 cites W3005650525 @default.
- W3204221214 cites W3044738063 @default.
- W3204221214 cites W3090212082 @default.
- W3204221214 cites W3091304180 @default.
- W3204221214 cites W3095848620 @default.
- W3204221214 doi "https://doi.org/10.1007/978-3-030-87196-3_42" @default.
- W3204221214 hasPublicationYear "2021" @default.
- W3204221214 type Work @default.
- W3204221214 sameAs 3204221214 @default.
- W3204221214 citedByCount "17" @default.
- W3204221214 countsByYear W32042212142022 @default.
- W3204221214 countsByYear W32042212142023 @default.
- W3204221214 crossrefType "book-chapter" @default.
- W3204221214 hasAuthorship W3204221214A5003642180 @default.
- W3204221214 hasAuthorship W3204221214A5009301235 @default.
- W3204221214 hasAuthorship W3204221214A5021875517 @default.
- W3204221214 hasAuthorship W3204221214A5030763508 @default.
- W3204221214 hasAuthorship W3204221214A5041675502 @default.
- W3204221214 hasAuthorship W3204221214A5072543841 @default.
- W3204221214 hasAuthorship W3204221214A5089126739 @default.
- W3204221214 hasConcept C119857082 @default.
- W3204221214 hasConcept C124504099 @default.
- W3204221214 hasConcept C153083717 @default.
- W3204221214 hasConcept C153180895 @default.
- W3204221214 hasConcept C154945302 @default.
- W3204221214 hasConcept C162324750 @default.
- W3204221214 hasConcept C187736073 @default.
- W3204221214 hasConcept C2776145971 @default.
- W3204221214 hasConcept C2776321320 @default.
- W3204221214 hasConcept C2776436953 @default.
- W3204221214 hasConcept C2780451532 @default.
- W3204221214 hasConcept C41008148 @default.
- W3204221214 hasConcept C89600930 @default.
- W3204221214 hasConceptScore W3204221214C119857082 @default.
- W3204221214 hasConceptScore W3204221214C124504099 @default.
- W3204221214 hasConceptScore W3204221214C153083717 @default.
- W3204221214 hasConceptScore W3204221214C153180895 @default.
- W3204221214 hasConceptScore W3204221214C154945302 @default.
- W3204221214 hasConceptScore W3204221214C162324750 @default.
- W3204221214 hasConceptScore W3204221214C187736073 @default.
- W3204221214 hasConceptScore W3204221214C2776145971 @default.
- W3204221214 hasConceptScore W3204221214C2776321320 @default.
- W3204221214 hasConceptScore W3204221214C2776436953 @default.
- W3204221214 hasConceptScore W3204221214C2780451532 @default.
- W3204221214 hasConceptScore W3204221214C41008148 @default.
- W3204221214 hasConceptScore W3204221214C89600930 @default.
- W3204221214 hasLocation W32042212141 @default.
- W3204221214 hasOpenAccess W3204221214 @default.
- W3204221214 hasPrimaryLocation W32042212141 @default.
- W3204221214 hasRelatedWork W2218034408 @default.
- W3204221214 hasRelatedWork W2263699433 @default.
- W3204221214 hasRelatedWork W2361861616 @default.
- W3204221214 hasRelatedWork W2377979023 @default.
- W3204221214 hasRelatedWork W2392921965 @default.
- W3204221214 hasRelatedWork W2798287483 @default.
- W3204221214 hasRelatedWork W2950181282 @default.
- W3204221214 hasRelatedWork W3210196349 @default.
- W3204221214 hasRelatedWork W4214728004 @default.
- W3204221214 hasRelatedWork W4221146302 @default.
- W3204221214 isParatext "false" @default.
- W3204221214 isRetracted "false" @default.
- W3204221214 magId "3204221214" @default.
- W3204221214 workType "book-chapter" @default.