Matches in SemOpenAlex for { <https://semopenalex.org/work/W4205604796> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4205604796 abstract "We describe a multi-source and unsupervised domain adaptation method using Sinkhorn barycenters, which, given the labeled data in multi-source domains and unlabeled data in a target domain, uses the optimal transport Sinkhorn distance to measure gaps between data distributions in the source and target domains. For end-to-end classification learning, the feature extractor and classifier are simultaneously estimated on the basis of two criteria: the minimization of the Sinkhorn distance for the source and target domains and the minimization of the classification loss for the source domains. The first criterion is based on the assumptions that domain-invariant features would be captured in a latent feature space obtained by minimizing the Sinkhorn distance among all domains and that the space would be close to the Sinkhorn barycenter. Experiments on image classification using the Digit-Five dataset, which is comprised of digit datasets from five different domains, demonstrated that our method outperforms other state-of-the-art methods." @default.
- W4205604796 created "2022-01-26" @default.
- W4205604796 creator A5015817857 @default.
- W4205604796 creator A5067714865 @default.
- W4205604796 creator A5071075728 @default.
- W4205604796 date "2021-08-23" @default.
- W4205604796 modified "2023-09-28" @default.
- W4205604796 title "Multi-Source Domain Adaptation with Sinkhorn Barycenter" @default.
- W4205604796 cites W1968333723 @default.
- W4205604796 cites W2036996178 @default.
- W4205604796 cites W2104094955 @default.
- W4205604796 cites W2110158442 @default.
- W4205604796 cites W2112796928 @default.
- W4205604796 cites W2169529055 @default.
- W4205604796 cites W2586686153 @default.
- W4205604796 cites W2593539611 @default.
- W4205604796 cites W2605146283 @default.
- W4205604796 cites W2884771968 @default.
- W4205604796 cites W2943996654 @default.
- W4205604796 cites W2963168418 @default.
- W4205604796 cites W2963506806 @default.
- W4205604796 cites W2964266860 @default.
- W4205604796 cites W2981720610 @default.
- W4205604796 doi "https://doi.org/10.23919/eusipco54536.2021.9615974" @default.
- W4205604796 hasPublicationYear "2021" @default.
- W4205604796 type Work @default.
- W4205604796 citedByCount "0" @default.
- W4205604796 crossrefType "proceedings-article" @default.
- W4205604796 hasAuthorship W4205604796A5015817857 @default.
- W4205604796 hasAuthorship W4205604796A5067714865 @default.
- W4205604796 hasAuthorship W4205604796A5071075728 @default.
- W4205604796 hasConcept C11413529 @default.
- W4205604796 hasConcept C117978034 @default.
- W4205604796 hasConcept C127413603 @default.
- W4205604796 hasConcept C134306372 @default.
- W4205604796 hasConcept C147764199 @default.
- W4205604796 hasConcept C153180895 @default.
- W4205604796 hasConcept C154945302 @default.
- W4205604796 hasConcept C190470478 @default.
- W4205604796 hasConcept C199360897 @default.
- W4205604796 hasConcept C21880701 @default.
- W4205604796 hasConcept C33923547 @default.
- W4205604796 hasConcept C36503486 @default.
- W4205604796 hasConcept C37914503 @default.
- W4205604796 hasConcept C41008148 @default.
- W4205604796 hasConcept C83665646 @default.
- W4205604796 hasConcept C95623464 @default.
- W4205604796 hasConceptScore W4205604796C11413529 @default.
- W4205604796 hasConceptScore W4205604796C117978034 @default.
- W4205604796 hasConceptScore W4205604796C127413603 @default.
- W4205604796 hasConceptScore W4205604796C134306372 @default.
- W4205604796 hasConceptScore W4205604796C147764199 @default.
- W4205604796 hasConceptScore W4205604796C153180895 @default.
- W4205604796 hasConceptScore W4205604796C154945302 @default.
- W4205604796 hasConceptScore W4205604796C190470478 @default.
- W4205604796 hasConceptScore W4205604796C199360897 @default.
- W4205604796 hasConceptScore W4205604796C21880701 @default.
- W4205604796 hasConceptScore W4205604796C33923547 @default.
- W4205604796 hasConceptScore W4205604796C36503486 @default.
- W4205604796 hasConceptScore W4205604796C37914503 @default.
- W4205604796 hasConceptScore W4205604796C41008148 @default.
- W4205604796 hasConceptScore W4205604796C83665646 @default.
- W4205604796 hasConceptScore W4205604796C95623464 @default.
- W4205604796 hasLocation W42056047961 @default.
- W4205604796 hasOpenAccess W4205604796 @default.
- W4205604796 hasPrimaryLocation W42056047961 @default.
- W4205604796 hasRelatedWork W1547978154 @default.
- W4205604796 hasRelatedWork W2001652754 @default.
- W4205604796 hasRelatedWork W2160451891 @default.
- W4205604796 hasRelatedWork W2275058042 @default.
- W4205604796 hasRelatedWork W2549006548 @default.
- W4205604796 hasRelatedWork W2765332597 @default.
- W4205604796 hasRelatedWork W2783820472 @default.
- W4205604796 hasRelatedWork W2994855682 @default.
- W4205604796 hasRelatedWork W3183327164 @default.
- W4205604796 hasRelatedWork W4214932115 @default.
- W4205604796 isParatext "false" @default.
- W4205604796 isRetracted "false" @default.
- W4205604796 workType "article" @default.