Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308385509> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4308385509 endingPage "109154" @default.
- W4308385509 startingPage "109154" @default.
- W4308385509 abstract "Unsupervised Domain Adaptation transfers knowledge from the source domain to the target domain. It makes remarkable progress in alleviating the label-shortage problem in machine learning. Existing methods focus on aligning the two domain distributions directly. However, due to domain discrepancy, there may be some samples in the source domain being unnecessary or even harmful to the target tasks. Avoiding transferring knowledge from these samples is crucial. Existing researches are limited in this area. To this end, we propose a new unsupervised domain adaptation approach named the prototype-guided feature learning. The proposed method contains three main innovations. Firstly, we propose to utilize the more representative source-domain samples, class prototypes, to learn a domain-invariant subspace with the target samples. Secondly, the modified nearest class prototype method is proposed to predict the target samples by exploiting the structural information of the target domain efficiently. Thirdly, a multi-stage label filtering method is proposed to alleviate the mislabeling problem during training. Extensive experiments manifest that our method is competitive compared to the current mainstream unsupervised domain adaptive methods." @default.
- W4308385509 created "2022-11-11" @default.
- W4308385509 creator A5000102478 @default.
- W4308385509 creator A5025548769 @default.
- W4308385509 creator A5035064408 @default.
- W4308385509 creator A5046223852 @default.
- W4308385509 creator A5086131621 @default.
- W4308385509 date "2023-03-01" @default.
- W4308385509 modified "2023-10-14" @default.
- W4308385509 title "Prototype-Guided Feature Learning for Unsupervised Domain Adaptation" @default.
- W4308385509 cites W1982696459 @default.
- W4308385509 cites W2085269372 @default.
- W4308385509 cites W2100664256 @default.
- W4308385509 cites W2115403315 @default.
- W4308385509 cites W2801443642 @default.
- W4308385509 cites W2939571759 @default.
- W4308385509 cites W2979509742 @default.
- W4308385509 cites W2999659281 @default.
- W4308385509 cites W3003622071 @default.
- W4308385509 cites W3082441598 @default.
- W4308385509 cites W3119745626 @default.
- W4308385509 cites W3135939397 @default.
- W4308385509 cites W3200441932 @default.
- W4308385509 cites W3201231642 @default.
- W4308385509 cites W3205907427 @default.
- W4308385509 cites W4214564152 @default.
- W4308385509 cites W4220792900 @default.
- W4308385509 cites W4220868778 @default.
- W4308385509 doi "https://doi.org/10.1016/j.patcog.2022.109154" @default.
- W4308385509 hasPublicationYear "2023" @default.
- W4308385509 type Work @default.
- W4308385509 citedByCount "4" @default.
- W4308385509 countsByYear W43083855092023 @default.
- W4308385509 crossrefType "journal-article" @default.
- W4308385509 hasAuthorship W4308385509A5000102478 @default.
- W4308385509 hasAuthorship W4308385509A5025548769 @default.
- W4308385509 hasAuthorship W4308385509A5035064408 @default.
- W4308385509 hasAuthorship W4308385509A5046223852 @default.
- W4308385509 hasAuthorship W4308385509A5086131621 @default.
- W4308385509 hasConcept C119857082 @default.
- W4308385509 hasConcept C120665830 @default.
- W4308385509 hasConcept C121332964 @default.
- W4308385509 hasConcept C134306372 @default.
- W4308385509 hasConcept C138885662 @default.
- W4308385509 hasConcept C153180895 @default.
- W4308385509 hasConcept C154945302 @default.
- W4308385509 hasConcept C192209626 @default.
- W4308385509 hasConcept C2776401178 @default.
- W4308385509 hasConcept C2776434776 @default.
- W4308385509 hasConcept C32834561 @default.
- W4308385509 hasConcept C33923547 @default.
- W4308385509 hasConcept C36503486 @default.
- W4308385509 hasConcept C41008148 @default.
- W4308385509 hasConcept C41895202 @default.
- W4308385509 hasConcept C8038995 @default.
- W4308385509 hasConcept C95623464 @default.
- W4308385509 hasConceptScore W4308385509C119857082 @default.
- W4308385509 hasConceptScore W4308385509C120665830 @default.
- W4308385509 hasConceptScore W4308385509C121332964 @default.
- W4308385509 hasConceptScore W4308385509C134306372 @default.
- W4308385509 hasConceptScore W4308385509C138885662 @default.
- W4308385509 hasConceptScore W4308385509C153180895 @default.
- W4308385509 hasConceptScore W4308385509C154945302 @default.
- W4308385509 hasConceptScore W4308385509C192209626 @default.
- W4308385509 hasConceptScore W4308385509C2776401178 @default.
- W4308385509 hasConceptScore W4308385509C2776434776 @default.
- W4308385509 hasConceptScore W4308385509C32834561 @default.
- W4308385509 hasConceptScore W4308385509C33923547 @default.
- W4308385509 hasConceptScore W4308385509C36503486 @default.
- W4308385509 hasConceptScore W4308385509C41008148 @default.
- W4308385509 hasConceptScore W4308385509C41895202 @default.
- W4308385509 hasConceptScore W4308385509C8038995 @default.
- W4308385509 hasConceptScore W4308385509C95623464 @default.
- W4308385509 hasFunder F4320321001 @default.
- W4308385509 hasFunder F4320324173 @default.
- W4308385509 hasFunder F4320335443 @default.
- W4308385509 hasLocation W43083855091 @default.
- W4308385509 hasOpenAccess W4308385509 @default.
- W4308385509 hasPrimaryLocation W43083855091 @default.
- W4308385509 hasRelatedWork W2042327336 @default.
- W4308385509 hasRelatedWork W2065962751 @default.
- W4308385509 hasRelatedWork W2543161807 @default.
- W4308385509 hasRelatedWork W2546942002 @default.
- W4308385509 hasRelatedWork W3046775127 @default.
- W4308385509 hasRelatedWork W3123344745 @default.
- W4308385509 hasRelatedWork W3196155444 @default.
- W4308385509 hasRelatedWork W3209574120 @default.
- W4308385509 hasRelatedWork W4285260836 @default.
- W4308385509 hasRelatedWork W4386462264 @default.
- W4308385509 hasVolume "135" @default.
- W4308385509 isParatext "false" @default.
- W4308385509 isRetracted "false" @default.
- W4308385509 workType "article" @default.