Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295915684> ?p ?o ?g. }
- W4295915684 endingPage "361" @default.
- W4295915684 startingPage "351" @default.
- W4295915684 abstract "Accurate segmentation of retinal fluids in 3D Optical Coherence Tomography images is key for diagnosis and personalized treatment of eye diseases. While deep learning has been successful at this task, trained supervised models often fail for images that do not resemble labeled examples, e.g. for images acquired using different devices. We hereby propose a novel semi-supervised learning framework for segmentation of volumetric images from new unlabeled domains. We jointly use supervised and contrastive learning, also introducing a contrastive pairing scheme that leverages similarity between nearby slices in 3D. In addition, we propose channel-wise aggregation as an alternative to conventional spatial-pooling aggregation for contrastive feature map projection. We evaluate our methods for domain adaptation from a (labeled) source domain to an (unlabeled) target domain, each containing images acquired with different acquisition devices. In the target domain, our method achieves a Dice coefficient 13.8% higher than SimCLR (a state-of-the-art contrastive framework), and leads to results comparable to an upper bound with supervised training in that domain. In the source domain, our model also improves the results by 5.4% Dice, by successfully leveraging information from many unlabeled images." @default.
- W4295915684 created "2022-09-16" @default.
- W4295915684 creator A5001369576 @default.
- W4295915684 creator A5016083472 @default.
- W4295915684 creator A5016658563 @default.
- W4295915684 creator A5019868420 @default.
- W4295915684 creator A5053308385 @default.
- W4295915684 creator A5059541679 @default.
- W4295915684 creator A5069892905 @default.
- W4295915684 creator A5073156743 @default.
- W4295915684 creator A5076237050 @default.
- W4295915684 creator A5085729099 @default.
- W4295915684 date "2022-01-01" @default.
- W4295915684 modified "2023-10-06" @default.
- W4295915684 title "Unsupervised Domain Adaptation with Contrastive Learning for OCT Segmentation" @default.
- W4295915684 cites W1458919156 @default.
- W4295915684 cites W1901129140 @default.
- W4295915684 cites W2108598243 @default.
- W4295915684 cites W2474279305 @default.
- W4295915684 cites W2772059204 @default.
- W4295915684 cites W2786808285 @default.
- W4295915684 cites W2886281300 @default.
- W4295915684 cites W2919070891 @default.
- W4295915684 cites W2962713370 @default.
- W4295915684 cites W2970140852 @default.
- W4295915684 cites W3035524453 @default.
- W4295915684 cites W3131357918 @default.
- W4295915684 cites W3159481202 @default.
- W4295915684 cites W3169295182 @default.
- W4295915684 cites W3171007011 @default.
- W4295915684 cites W3203953535 @default.
- W4295915684 cites W4250482878 @default.
- W4295915684 doi "https://doi.org/10.1007/978-3-031-16452-1_34" @default.
- W4295915684 hasPublicationYear "2022" @default.
- W4295915684 type Work @default.
- W4295915684 citedByCount "2" @default.
- W4295915684 crossrefType "book-chapter" @default.
- W4295915684 hasAuthorship W4295915684A5001369576 @default.
- W4295915684 hasAuthorship W4295915684A5016083472 @default.
- W4295915684 hasAuthorship W4295915684A5016658563 @default.
- W4295915684 hasAuthorship W4295915684A5019868420 @default.
- W4295915684 hasAuthorship W4295915684A5053308385 @default.
- W4295915684 hasAuthorship W4295915684A5059541679 @default.
- W4295915684 hasAuthorship W4295915684A5069892905 @default.
- W4295915684 hasAuthorship W4295915684A5073156743 @default.
- W4295915684 hasAuthorship W4295915684A5076237050 @default.
- W4295915684 hasAuthorship W4295915684A5085729099 @default.
- W4295915684 hasBestOaLocation W42959156842 @default.
- W4295915684 hasConcept C103278499 @default.
- W4295915684 hasConcept C115961682 @default.
- W4295915684 hasConcept C124504099 @default.
- W4295915684 hasConcept C134306372 @default.
- W4295915684 hasConcept C138885662 @default.
- W4295915684 hasConcept C153180895 @default.
- W4295915684 hasConcept C154945302 @default.
- W4295915684 hasConcept C163892561 @default.
- W4295915684 hasConcept C2776401178 @default.
- W4295915684 hasConcept C2776434776 @default.
- W4295915684 hasConcept C31972630 @default.
- W4295915684 hasConcept C33923547 @default.
- W4295915684 hasConcept C36503486 @default.
- W4295915684 hasConcept C41008148 @default.
- W4295915684 hasConcept C41895202 @default.
- W4295915684 hasConcept C70437156 @default.
- W4295915684 hasConcept C89600930 @default.
- W4295915684 hasConcept C95623464 @default.
- W4295915684 hasConceptScore W4295915684C103278499 @default.
- W4295915684 hasConceptScore W4295915684C115961682 @default.
- W4295915684 hasConceptScore W4295915684C124504099 @default.
- W4295915684 hasConceptScore W4295915684C134306372 @default.
- W4295915684 hasConceptScore W4295915684C138885662 @default.
- W4295915684 hasConceptScore W4295915684C153180895 @default.
- W4295915684 hasConceptScore W4295915684C154945302 @default.
- W4295915684 hasConceptScore W4295915684C163892561 @default.
- W4295915684 hasConceptScore W4295915684C2776401178 @default.
- W4295915684 hasConceptScore W4295915684C2776434776 @default.
- W4295915684 hasConceptScore W4295915684C31972630 @default.
- W4295915684 hasConceptScore W4295915684C33923547 @default.
- W4295915684 hasConceptScore W4295915684C36503486 @default.
- W4295915684 hasConceptScore W4295915684C41008148 @default.
- W4295915684 hasConceptScore W4295915684C41895202 @default.
- W4295915684 hasConceptScore W4295915684C70437156 @default.
- W4295915684 hasConceptScore W4295915684C89600930 @default.
- W4295915684 hasConceptScore W4295915684C95623464 @default.
- W4295915684 hasLocation W42959156841 @default.
- W4295915684 hasLocation W42959156842 @default.
- W4295915684 hasOpenAccess W4295915684 @default.
- W4295915684 hasPrimaryLocation W42959156841 @default.
- W4295915684 hasRelatedWork W1669643531 @default.
- W4295915684 hasRelatedWork W1982826852 @default.
- W4295915684 hasRelatedWork W2005437358 @default.
- W4295915684 hasRelatedWork W2008656436 @default.
- W4295915684 hasRelatedWork W2023558673 @default.
- W4295915684 hasRelatedWork W2110230079 @default.
- W4295915684 hasRelatedWork W2134924024 @default.
- W4295915684 hasRelatedWork W2517104666 @default.
- W4295915684 hasRelatedWork W2613186388 @default.
- W4295915684 hasRelatedWork W1967061043 @default.