Matches in SemOpenAlex for { <https://semopenalex.org/work/W3175150427> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3175150427 abstract "Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to an unlabeled and unseen target domain, which is usually trained on data from both domains. Access to the source domain data at the adaptation stage, however, is often limited, due to data storage or privacy issues. To alleviate this, in this work, we target source free UDA for segmentation, and propose to adapt an ``off-the-shelf segmentation model pre-trained in the source domain to the target domain, with an adaptive batch-wise normalization statistics adaptation framework. Specifically, the domain-specific low-order batch statistics, i.e., mean and variance, are gradually adapted with an exponential momentum decay scheme, while the consistency of domain shareable high-order batch statistics, i.e., scaling and shifting parameters, is explicitly enforced by our optimization objective. The transferability of each channel is adaptively measured first from which to balance the contribution of each channel. Moreover, the proposed source free UDA framework is orthogonal to unsupervised learning methods, e.g., self-entropy minimization, which can thus be simply added on top of our framework. Extensive experiments on the BraTS 2018 database show that our source free UDA framework outperformed existing source-relaxed UDA methods for the cross-subtype UDA segmentation task and yielded comparable results for the cross-modality UDA segmentation task, compared with a supervised UDA methods with the source data." @default.
- W3175150427 created "2021-07-05" @default.
- W3175150427 creator A5002309775 @default.
- W3175150427 creator A5007259734 @default.
- W3175150427 creator A5013766979 @default.
- W3175150427 creator A5026108994 @default.
- W3175150427 creator A5053436378 @default.
- W3175150427 date "2021-06-23" @default.
- W3175150427 modified "2023-09-25" @default.
- W3175150427 title "Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentation" @default.
- W3175150427 cites W1641498739 @default.
- W3175150427 cites W1836465849 @default.
- W3175150427 cites W2145494108 @default.
- W3175150427 cites W2194775991 @default.
- W3175150427 cites W2607512710 @default.
- W3175150427 cites W2793888044 @default.
- W3175150427 cites W2884366600 @default.
- W3175150427 cites W2905562891 @default.
- W3175150427 cites W2913282330 @default.
- W3175150427 cites W2949813473 @default.
- W3175150427 cites W2962793481 @default.
- W3175150427 cites W2963797156 @default.
- W3175150427 cites W2963864946 @default.
- W3175150427 cites W2963870446 @default.
- W3175150427 cites W2970987681 @default.
- W3175150427 cites W2979647636 @default.
- W3175150427 cites W2980113592 @default.
- W3175150427 cites W2985406498 @default.
- W3175150427 cites W2993534970 @default.
- W3175150427 cites W2998802446 @default.
- W3175150427 cites W3013916134 @default.
- W3175150427 cites W3034240269 @default.
- W3175150427 cites W3034526587 @default.
- W3175150427 cites W3036246552 @default.
- W3175150427 cites W3039883906 @default.
- W3175150427 cites W3092433507 @default.
- W3175150427 cites W3118182541 @default.
- W3175150427 cites W3162278040 @default.
- W3175150427 cites W3164808843 @default.
- W3175150427 cites W3175703606 @default.
- W3175150427 cites W3176580854 @default.
- W3175150427 cites W3190537960 @default.
- W3175150427 cites W3198009109 @default.
- W3175150427 cites W3203972116 @default.
- W3175150427 doi "https://doi.org/10.48550/arxiv.2106.12497" @default.
- W3175150427 hasPublicationYear "2021" @default.
- W3175150427 type Work @default.
- W3175150427 sameAs 3175150427 @default.
- W3175150427 citedByCount "1" @default.
- W3175150427 countsByYear W31751504272021 @default.
- W3175150427 crossrefType "posted-content" @default.
- W3175150427 hasAuthorship W3175150427A5002309775 @default.
- W3175150427 hasAuthorship W3175150427A5007259734 @default.
- W3175150427 hasAuthorship W3175150427A5013766979 @default.
- W3175150427 hasAuthorship W3175150427A5026108994 @default.
- W3175150427 hasAuthorship W3175150427A5053436378 @default.
- W3175150427 hasBestOaLocation W31751504271 @default.
- W3175150427 hasConcept C111919701 @default.
- W3175150427 hasConcept C119857082 @default.
- W3175150427 hasConcept C124101348 @default.
- W3175150427 hasConcept C136886441 @default.
- W3175150427 hasConcept C144024400 @default.
- W3175150427 hasConcept C150899416 @default.
- W3175150427 hasConcept C153180895 @default.
- W3175150427 hasConcept C154945302 @default.
- W3175150427 hasConcept C19165224 @default.
- W3175150427 hasConcept C41008148 @default.
- W3175150427 hasConcept C43126263 @default.
- W3175150427 hasConcept C89600930 @default.
- W3175150427 hasConceptScore W3175150427C111919701 @default.
- W3175150427 hasConceptScore W3175150427C119857082 @default.
- W3175150427 hasConceptScore W3175150427C124101348 @default.
- W3175150427 hasConceptScore W3175150427C136886441 @default.
- W3175150427 hasConceptScore W3175150427C144024400 @default.
- W3175150427 hasConceptScore W3175150427C150899416 @default.
- W3175150427 hasConceptScore W3175150427C153180895 @default.
- W3175150427 hasConceptScore W3175150427C154945302 @default.
- W3175150427 hasConceptScore W3175150427C19165224 @default.
- W3175150427 hasConceptScore W3175150427C41008148 @default.
- W3175150427 hasConceptScore W3175150427C43126263 @default.
- W3175150427 hasConceptScore W3175150427C89600930 @default.
- W3175150427 hasLocation W31751504271 @default.
- W3175150427 hasLocation W31751504272 @default.
- W3175150427 hasOpenAccess W3175150427 @default.
- W3175150427 hasPrimaryLocation W31751504271 @default.
- W3175150427 hasRelatedWork W1507687735 @default.
- W3175150427 hasRelatedWork W1863050261 @default.
- W3175150427 hasRelatedWork W2016839265 @default.
- W3175150427 hasRelatedWork W2026355170 @default.
- W3175150427 hasRelatedWork W2946038180 @default.
- W3175150427 hasRelatedWork W4206076898 @default.
- W3175150427 hasRelatedWork W4281382123 @default.
- W3175150427 hasRelatedWork W4308262314 @default.
- W3175150427 hasRelatedWork W4313207663 @default.
- W3175150427 hasRelatedWork W2508457823 @default.
- W3175150427 isParatext "false" @default.
- W3175150427 isRetracted "false" @default.
- W3175150427 magId "3175150427" @default.
- W3175150427 workType "article" @default.