FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203717475> ?p ?o ?g. }

• W3203717475 endingPage "230" @default.
• W3203717475 startingPage "221" @default.
• W3203717475 abstract "The success of deep learning heavily depends on the availability of large labeled training sets. However, it is hard to get large labeled datasets in medical image domain because of the strict privacy concern and costly labeling efforts. Contrastive learning, an unsupervised learning technique, has been proved powerful in learning image-level representations from unlabeled data. The learned encoder can then be transferred or fine-tuned to improve the performance of downstream tasks with limited labels. A critical step in contrastive learning is the generation of contrastive data pairs, which is relatively simple for natural image classification but quite challenging for medical image segmentation due to the existence of the same tissue or organ across the dataset. As a result, when applied to medical image segmentation, most state-of-the-art contrastive learning frameworks inevitably introduce a lot of false negative pairs and result in degraded segmentation quality. To address this issue, we propose a novel positional contrastive learning (PCL) framework to generate contrastive data pairs by leveraging the position information in volumetric medical images. Experimental results on CT and MRI datasets demonstrate that the proposed PCL method can substantially improve the segmentation performance compared to existing methods in both semi-supervised setting and transfer learning setting. (Code available at github.com/dewenzeng/positional_cl)." @default.
• W3203717475 created "2021-10-11" @default.
• W3203717475 creator A5000141831 @default.
• W3203717475 creator A5003562224 @default.
• W3203717475 creator A5019020335 @default.
• W3203717475 creator A5027969288 @default.
• W3203717475 creator A5029085468 @default.
• W3203717475 creator A5037197076 @default.
• W3203717475 creator A5066534595 @default.
• W3203717475 creator A5074593997 @default.
• W3203717475 creator A5086347026 @default.
• W3203717475 date "2021-01-01" @default.
• W3203717475 modified "2023-10-03" @default.
• W3203717475 title "Positional Contrastive Learning for Volumetric Medical Image Segmentation" @default.
• W3203717475 cites W1901129140 @default.
• W3203717475 cites W2082718270 @default.
• W3203717475 cites W2266059378 @default.
• W3203717475 cites W2291593693 @default.
• W3203717475 cites W2804047627 @default.
• W3203717475 cites W2912989244 @default.
• W3203717475 cites W2963395421 @default.
• W3203717475 cites W2979542579 @default.
• W3203717475 cites W2979579242 @default.
• W3203717475 cites W3006170182 @default.
• W3203717475 cites W3034781633 @default.
• W3203717475 cites W3035524453 @default.
• W3203717475 cites W3051093578 @default.
• W3203717475 cites W3092507194 @default.
• W3203717475 cites W3094123278 @default.
• W3203717475 cites W3096368178 @default.
• W3203717475 cites W3108655343 @default.
• W3203717475 doi "https://doi.org/10.1007/978-3-030-87196-3_21" @default.
• W3203717475 hasPublicationYear "2021" @default.
• W3203717475 type Work @default.
• W3203717475 sameAs 3203717475 @default.
• W3203717475 citedByCount "22" @default.
• W3203717475 countsByYear W32037174752022 @default.
• W3203717475 countsByYear W32037174752023 @default.
• W3203717475 crossrefType "book-chapter" @default.
• W3203717475 hasAuthorship W3203717475A5000141831 @default.
• W3203717475 hasAuthorship W3203717475A5003562224 @default.
• W3203717475 hasAuthorship W3203717475A5019020335 @default.
• W3203717475 hasAuthorship W3203717475A5027969288 @default.
• W3203717475 hasAuthorship W3203717475A5029085468 @default.
• W3203717475 hasAuthorship W3203717475A5037197076 @default.
• W3203717475 hasAuthorship W3203717475A5066534595 @default.
• W3203717475 hasAuthorship W3203717475A5074593997 @default.
• W3203717475 hasAuthorship W3203717475A5086347026 @default.
• W3203717475 hasBestOaLocation W32037174752 @default.
• W3203717475 hasConcept C101738243 @default.
• W3203717475 hasConcept C108583219 @default.
• W3203717475 hasConcept C111919701 @default.
• W3203717475 hasConcept C115961682 @default.
• W3203717475 hasConcept C118505674 @default.
• W3203717475 hasConcept C119857082 @default.
• W3203717475 hasConcept C124504099 @default.
• W3203717475 hasConcept C134306372 @default.
• W3203717475 hasConcept C150899416 @default.
• W3203717475 hasConcept C153180895 @default.
• W3203717475 hasConcept C154945302 @default.
• W3203717475 hasConcept C31601959 @default.
• W3203717475 hasConcept C33923547 @default.
• W3203717475 hasConcept C36503486 @default.
• W3203717475 hasConcept C41008148 @default.
• W3203717475 hasConcept C89600930 @default.
• W3203717475 hasConceptScore W3203717475C101738243 @default.
• W3203717475 hasConceptScore W3203717475C108583219 @default.
• W3203717475 hasConceptScore W3203717475C111919701 @default.
• W3203717475 hasConceptScore W3203717475C115961682 @default.
• W3203717475 hasConceptScore W3203717475C118505674 @default.
• W3203717475 hasConceptScore W3203717475C119857082 @default.
• W3203717475 hasConceptScore W3203717475C124504099 @default.
• W3203717475 hasConceptScore W3203717475C134306372 @default.
• W3203717475 hasConceptScore W3203717475C150899416 @default.
• W3203717475 hasConceptScore W3203717475C153180895 @default.
• W3203717475 hasConceptScore W3203717475C154945302 @default.
• W3203717475 hasConceptScore W3203717475C31601959 @default.
• W3203717475 hasConceptScore W3203717475C33923547 @default.
• W3203717475 hasConceptScore W3203717475C36503486 @default.
• W3203717475 hasConceptScore W3203717475C41008148 @default.
• W3203717475 hasConceptScore W3203717475C89600930 @default.
• W3203717475 hasLocation W32037174751 @default.
• W3203717475 hasLocation W32037174752 @default.
• W3203717475 hasOpenAccess W3203717475 @default.
• W3203717475 hasPrimaryLocation W32037174751 @default.
• W3203717475 hasRelatedWork W2946016983 @default.
• W3203717475 hasRelatedWork W2960184797 @default.
• W3203717475 hasRelatedWork W2960456850 @default.
• W3203717475 hasRelatedWork W3089025284 @default.
• W3203717475 hasRelatedWork W4224044423 @default.
• W3203717475 hasRelatedWork W4285827401 @default.
• W3203717475 hasRelatedWork W4292874285 @default.
• W3203717475 hasRelatedWork W4312200629 @default.
• W3203717475 hasRelatedWork W4317565044 @default.
• W3203717475 hasRelatedWork W4382286161 @default.
• W3203717475 isParatext "false" @default.
• W3203717475 isRetracted "false" @default.
• W3203717475 magId "3203717475" @default.

• next