Matches in SemOpenAlex for { <https://semopenalex.org/work/W2767179670> ?p ?o ?g. }
- W2767179670 abstract "In multimedia analysis, the task of domain adaptation is to adapt the feature representation learned in the source domain with rich label information to the target domain with less or even no label information. Significant research endeavors have been devoted to aligning the feature distributions between the source and the target domains in the top fully connected layers based on unsupervised DNN-based models. However, the domain adaptation has been arbitrarily constrained near the output ends of the DNN models, which thus brings about inadequate knowledge transfer in DNN-based domain adaptation process, especially near the input end. We develop an attention transfer process for convolutional domain adaptation. The domain discrepancy, measured in correlation alignment loss, is minimized on the second-order correlation statistics of the attention maps for both source and target domains. Then we propose Deep Unsupervised Convolutional Domain Adaptation DUCDA method, which jointly minimizes the supervised classification loss of labeled source data and the unsupervised correlation alignment loss measured on both convolutional layers and fully connected layers. The multi-layer domain adaptation process collaborately reinforces each individual domain adaptation component, and significantly enhances the generalization ability of the CNN models. Extensive cross-domain object classification experiments show DUCDA outperforms other state-of-the-art approaches, and validate the promising power of DUCDA towards large scale real world application." @default.
- W2767179670 created "2017-11-10" @default.
- W2767179670 creator A5001393670 @default.
- W2767179670 creator A5014774434 @default.
- W2767179670 creator A5028597017 @default.
- W2767179670 creator A5034112897 @default.
- W2767179670 date "2017-10-19" @default.
- W2767179670 modified "2023-10-13" @default.
- W2767179670 title "Deep Unsupervised Convolutional Domain Adaptation" @default.
- W2767179670 cites W1722318740 @default.
- W2767179670 cites W1920962657 @default.
- W2767179670 cites W1994488211 @default.
- W2767179670 cites W2031342017 @default.
- W2767179670 cites W2064447488 @default.
- W2767179670 cites W2096943734 @default.
- W2767179670 cites W2097117768 @default.
- W2767179670 cites W2104068492 @default.
- W2767179670 cites W2115403315 @default.
- W2767179670 cites W2128053425 @default.
- W2767179670 cites W2149466042 @default.
- W2767179670 cites W2155893237 @default.
- W2767179670 cites W2162583786 @default.
- W2767179670 cites W2162915993 @default.
- W2767179670 cites W2293078015 @default.
- W2767179670 cites W2962759496 @default.
- W2767179670 cites W2963954913 @default.
- W2767179670 cites W2998115938 @default.
- W2767179670 doi "https://doi.org/10.1145/3123266.3123292" @default.
- W2767179670 hasPublicationYear "2017" @default.
- W2767179670 type Work @default.
- W2767179670 sameAs 2767179670 @default.
- W2767179670 citedByCount "91" @default.
- W2767179670 countsByYear W27671796702018 @default.
- W2767179670 countsByYear W27671796702019 @default.
- W2767179670 countsByYear W27671796702020 @default.
- W2767179670 countsByYear W27671796702021 @default.
- W2767179670 countsByYear W27671796702022 @default.
- W2767179670 countsByYear W27671796702023 @default.
- W2767179670 crossrefType "proceedings-article" @default.
- W2767179670 hasAuthorship W2767179670A5001393670 @default.
- W2767179670 hasAuthorship W2767179670A5014774434 @default.
- W2767179670 hasAuthorship W2767179670A5028597017 @default.
- W2767179670 hasAuthorship W2767179670A5034112897 @default.
- W2767179670 hasConcept C119857082 @default.
- W2767179670 hasConcept C120665830 @default.
- W2767179670 hasConcept C121332964 @default.
- W2767179670 hasConcept C134306372 @default.
- W2767179670 hasConcept C138885662 @default.
- W2767179670 hasConcept C139807058 @default.
- W2767179670 hasConcept C150899416 @default.
- W2767179670 hasConcept C153180895 @default.
- W2767179670 hasConcept C154945302 @default.
- W2767179670 hasConcept C177148314 @default.
- W2767179670 hasConcept C17744445 @default.
- W2767179670 hasConcept C199539241 @default.
- W2767179670 hasConcept C2776359362 @default.
- W2767179670 hasConcept C2776401178 @default.
- W2767179670 hasConcept C2776434776 @default.
- W2767179670 hasConcept C33923547 @default.
- W2767179670 hasConcept C36503486 @default.
- W2767179670 hasConcept C41008148 @default.
- W2767179670 hasConcept C41895202 @default.
- W2767179670 hasConcept C52622490 @default.
- W2767179670 hasConcept C59404180 @default.
- W2767179670 hasConcept C81363708 @default.
- W2767179670 hasConcept C94625758 @default.
- W2767179670 hasConcept C95623464 @default.
- W2767179670 hasConceptScore W2767179670C119857082 @default.
- W2767179670 hasConceptScore W2767179670C120665830 @default.
- W2767179670 hasConceptScore W2767179670C121332964 @default.
- W2767179670 hasConceptScore W2767179670C134306372 @default.
- W2767179670 hasConceptScore W2767179670C138885662 @default.
- W2767179670 hasConceptScore W2767179670C139807058 @default.
- W2767179670 hasConceptScore W2767179670C150899416 @default.
- W2767179670 hasConceptScore W2767179670C153180895 @default.
- W2767179670 hasConceptScore W2767179670C154945302 @default.
- W2767179670 hasConceptScore W2767179670C177148314 @default.
- W2767179670 hasConceptScore W2767179670C17744445 @default.
- W2767179670 hasConceptScore W2767179670C199539241 @default.
- W2767179670 hasConceptScore W2767179670C2776359362 @default.
- W2767179670 hasConceptScore W2767179670C2776401178 @default.
- W2767179670 hasConceptScore W2767179670C2776434776 @default.
- W2767179670 hasConceptScore W2767179670C33923547 @default.
- W2767179670 hasConceptScore W2767179670C36503486 @default.
- W2767179670 hasConceptScore W2767179670C41008148 @default.
- W2767179670 hasConceptScore W2767179670C41895202 @default.
- W2767179670 hasConceptScore W2767179670C52622490 @default.
- W2767179670 hasConceptScore W2767179670C59404180 @default.
- W2767179670 hasConceptScore W2767179670C81363708 @default.
- W2767179670 hasConceptScore W2767179670C94625758 @default.
- W2767179670 hasConceptScore W2767179670C95623464 @default.
- W2767179670 hasLocation W27671796701 @default.
- W2767179670 hasOpenAccess W2767179670 @default.
- W2767179670 hasPrimaryLocation W27671796701 @default.
- W2767179670 hasRelatedWork W1569300204 @default.
- W2767179670 hasRelatedWork W189527659 @default.
- W2767179670 hasRelatedWork W2116397056 @default.
- W2767179670 hasRelatedWork W2285788670 @default.
- W2767179670 hasRelatedWork W2415731916 @default.
- W2767179670 hasRelatedWork W2748454020 @default.