Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224920105> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4224920105 abstract "The success of supervised deep learning heavily depends on large labeled datasets whose construction is often challenging in medical image analysis. Contrastive learning, a variant of self-supervised learning, is a potential solution to alleviate the strong demand for data annotation. In this work, we extend the contrastive learning framework to 3D volumetric medical imaging. Specifically, we propose (1) multiview contrasting strategy to maximize the mutual information between three views of 3D image to learn global representations and (2) long-short spatial contrasting strategy to learn local representations by matching a short spatial clip to a long spatial clip in the latent space. To combine these two strategies, we propose multiview long-short spatial contrastive learning (MLSSCL) framework, which can effectively learn generic 3D representations. Our extensive experiments on two brain Magnetic Resonance Imaging (MRI) datasets demonstrate that MLSSCL significantly outperforms learning from scratch and other self-supervised learning methods on both classification and segmentation tasks." @default.
- W4224920105 created "2022-04-28" @default.
- W4224920105 creator A5000245536 @default.
- W4224920105 creator A5017947172 @default.
- W4224920105 creator A5023183004 @default.
- W4224920105 creator A5062885337 @default.
- W4224920105 creator A5076200159 @default.
- W4224920105 creator A5085386009 @default.
- W4224920105 date "2022-05-23" @default.
- W4224920105 modified "2023-09-23" @default.
- W4224920105 title "Multiview Long-Short Spatial Contrastive Learning For 3D Medical Image Analysis" @default.
- W4224920105 cites W2575552683 @default.
- W4224920105 cites W2589409328 @default.
- W4224920105 cites W2900299818 @default.
- W4224920105 cites W2964744899 @default.
- W4224920105 cites W2979888373 @default.
- W4224920105 cites W3015473399 @default.
- W4224920105 cites W3016836174 @default.
- W4224920105 cites W3035524453 @default.
- W4224920105 cites W3108655343 @default.
- W4224920105 cites W3203607638 @default.
- W4224920105 doi "https://doi.org/10.1109/icassp43922.2022.9747913" @default.
- W4224920105 hasPublicationYear "2022" @default.
- W4224920105 type Work @default.
- W4224920105 citedByCount "0" @default.
- W4224920105 crossrefType "proceedings-article" @default.
- W4224920105 hasAuthorship W4224920105A5000245536 @default.
- W4224920105 hasAuthorship W4224920105A5017947172 @default.
- W4224920105 hasAuthorship W4224920105A5023183004 @default.
- W4224920105 hasAuthorship W4224920105A5062885337 @default.
- W4224920105 hasAuthorship W4224920105A5076200159 @default.
- W4224920105 hasAuthorship W4224920105A5085386009 @default.
- W4224920105 hasConcept C105795698 @default.
- W4224920105 hasConcept C108583219 @default.
- W4224920105 hasConcept C119857082 @default.
- W4224920105 hasConcept C124504099 @default.
- W4224920105 hasConcept C153180895 @default.
- W4224920105 hasConcept C154945302 @default.
- W4224920105 hasConcept C165064840 @default.
- W4224920105 hasConcept C31601959 @default.
- W4224920105 hasConcept C31972630 @default.
- W4224920105 hasConcept C33923547 @default.
- W4224920105 hasConcept C41008148 @default.
- W4224920105 hasConcept C89600930 @default.
- W4224920105 hasConceptScore W4224920105C105795698 @default.
- W4224920105 hasConceptScore W4224920105C108583219 @default.
- W4224920105 hasConceptScore W4224920105C119857082 @default.
- W4224920105 hasConceptScore W4224920105C124504099 @default.
- W4224920105 hasConceptScore W4224920105C153180895 @default.
- W4224920105 hasConceptScore W4224920105C154945302 @default.
- W4224920105 hasConceptScore W4224920105C165064840 @default.
- W4224920105 hasConceptScore W4224920105C31601959 @default.
- W4224920105 hasConceptScore W4224920105C31972630 @default.
- W4224920105 hasConceptScore W4224920105C33923547 @default.
- W4224920105 hasConceptScore W4224920105C41008148 @default.
- W4224920105 hasConceptScore W4224920105C89600930 @default.
- W4224920105 hasFunder F4320321001 @default.
- W4224920105 hasFunder F4320329860 @default.
- W4224920105 hasFunder F4320335787 @default.
- W4224920105 hasLocation W42249201051 @default.
- W4224920105 hasOpenAccess W4224920105 @default.
- W4224920105 hasPrimaryLocation W42249201051 @default.
- W4224920105 hasRelatedWork W10101583 @default.
- W4224920105 hasRelatedWork W11130107 @default.
- W4224920105 hasRelatedWork W12703013 @default.
- W4224920105 hasRelatedWork W12718294 @default.
- W4224920105 hasRelatedWork W14128562 @default.
- W4224920105 hasRelatedWork W1446482 @default.
- W4224920105 hasRelatedWork W2526871 @default.
- W4224920105 hasRelatedWork W4412456 @default.
- W4224920105 hasRelatedWork W6572092 @default.
- W4224920105 hasRelatedWork W3000238 @default.
- W4224920105 isParatext "false" @default.
- W4224920105 isRetracted "false" @default.
- W4224920105 workType "article" @default.