Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100804201> ?p ?o ?g. }
- W3100804201 endingPage "2744" @default.
- W3100804201 startingPage "2732" @default.
- W3100804201 abstract "Domain adaptation aims to transfer knowledge from a domain with adequate labeled samples to a domain with scarce labeled samples. Prior research has introduced various open set domain adaptation settings in the literature to extend the applications of domain adaptation methods in real-world scenarios. This paper focuses on the type of open set domain adaptation setting where the target domain has both private (‘unknown classes’) label space and the shared (‘known classes’) label space. However, the source domain only has the ‘known classes’ label space. Prevalent distribution-matching domain adaptation methods are inadequate in such a setting that demands adaptation from a smaller source domain to a larger and diverse target domain with more classes. For addressing this specific open set domain adaptation setting, prior research introduces a domain adversarial model that uses a fixed threshold for distinguishing known from unknown target samples and lacks at handling negative transfers. We extend their adversarial model and propose a novel adversarial domain adaptation model with multiple auxiliary classifiers. The proposed multi-classifier structure introduces a weighting module that evaluates distinctive domain characteristics for assigning the target samples with weights which are more representative to whether they are likely to belong to the known and unknown classes to encourage positive transfers during adversarial training and simultaneously reduces the domain gap between the shared classes of the source and target domains. A thorough experimental investigation shows that our proposed method outperforms existing domain adaptation methods on a number of domain adaptation datasets." @default.
- W3100804201 created "2020-11-23" @default.
- W3100804201 creator A5002219416 @default.
- W3100804201 creator A5007657733 @default.
- W3100804201 creator A5010357798 @default.
- W3100804201 creator A5064846157 @default.
- W3100804201 creator A5083883712 @default.
- W3100804201 date "2021-01-01" @default.
- W3100804201 modified "2023-10-01" @default.
- W3100804201 title "Adversarial Network With Multiple Classifiers for Open Set Domain Adaptation" @default.
- W3100804201 cites W2097117768 @default.
- W3100804201 cites W2115403315 @default.
- W3100804201 cites W2117539524 @default.
- W3100804201 cites W2120149881 @default.
- W3100804201 cites W2165698076 @default.
- W3100804201 cites W2194775991 @default.
- W3100804201 cites W2584009249 @default.
- W3100804201 cites W2593768305 @default.
- W3100804201 cites W2605488490 @default.
- W3100804201 cites W2617027347 @default.
- W3100804201 cites W2627183927 @default.
- W3100804201 cites W2744915377 @default.
- W3100804201 cites W2773004715 @default.
- W3100804201 cites W2779610669 @default.
- W3100804201 cites W2798593490 @default.
- W3100804201 cites W2801477643 @default.
- W3100804201 cites W2885018852 @default.
- W3100804201 cites W2892946488 @default.
- W3100804201 cites W2919206487 @default.
- W3100804201 cites W2948069880 @default.
- W3100804201 cites W2948429981 @default.
- W3100804201 cites W2953226914 @default.
- W3100804201 cites W2955547856 @default.
- W3100804201 cites W2962687275 @default.
- W3100804201 cites W2962793481 @default.
- W3100804201 cites W2962835731 @default.
- W3100804201 cites W2962986791 @default.
- W3100804201 cites W2963149653 @default.
- W3100804201 cites W2963403405 @default.
- W3100804201 cites W2964057616 @default.
- W3100804201 cites W2964109570 @default.
- W3100804201 cites W2982120826 @default.
- W3100804201 cites W2988014923 @default.
- W3100804201 doi "https://doi.org/10.1109/tmm.2020.3016126" @default.
- W3100804201 hasPublicationYear "2021" @default.
- W3100804201 type Work @default.
- W3100804201 sameAs 3100804201 @default.
- W3100804201 citedByCount "20" @default.
- W3100804201 countsByYear W31008042012021 @default.
- W3100804201 countsByYear W31008042012022 @default.
- W3100804201 countsByYear W31008042012023 @default.
- W3100804201 crossrefType "journal-article" @default.
- W3100804201 hasAuthorship W3100804201A5002219416 @default.
- W3100804201 hasAuthorship W3100804201A5007657733 @default.
- W3100804201 hasAuthorship W3100804201A5010357798 @default.
- W3100804201 hasAuthorship W3100804201A5064846157 @default.
- W3100804201 hasAuthorship W3100804201A5083883712 @default.
- W3100804201 hasBestOaLocation W31008042012 @default.
- W3100804201 hasConcept C118615104 @default.
- W3100804201 hasConcept C119857082 @default.
- W3100804201 hasConcept C120665830 @default.
- W3100804201 hasConcept C121332964 @default.
- W3100804201 hasConcept C124101348 @default.
- W3100804201 hasConcept C126838900 @default.
- W3100804201 hasConcept C134306372 @default.
- W3100804201 hasConcept C139807058 @default.
- W3100804201 hasConcept C153180895 @default.
- W3100804201 hasConcept C154945302 @default.
- W3100804201 hasConcept C177264268 @default.
- W3100804201 hasConcept C183115368 @default.
- W3100804201 hasConcept C199360897 @default.
- W3100804201 hasConcept C2776434776 @default.
- W3100804201 hasConcept C33923547 @default.
- W3100804201 hasConcept C36503486 @default.
- W3100804201 hasConcept C37736160 @default.
- W3100804201 hasConcept C41008148 @default.
- W3100804201 hasConcept C42357961 @default.
- W3100804201 hasConcept C71924100 @default.
- W3100804201 hasConcept C95623464 @default.
- W3100804201 hasConceptScore W3100804201C118615104 @default.
- W3100804201 hasConceptScore W3100804201C119857082 @default.
- W3100804201 hasConceptScore W3100804201C120665830 @default.
- W3100804201 hasConceptScore W3100804201C121332964 @default.
- W3100804201 hasConceptScore W3100804201C124101348 @default.
- W3100804201 hasConceptScore W3100804201C126838900 @default.
- W3100804201 hasConceptScore W3100804201C134306372 @default.
- W3100804201 hasConceptScore W3100804201C139807058 @default.
- W3100804201 hasConceptScore W3100804201C153180895 @default.
- W3100804201 hasConceptScore W3100804201C154945302 @default.
- W3100804201 hasConceptScore W3100804201C177264268 @default.
- W3100804201 hasConceptScore W3100804201C183115368 @default.
- W3100804201 hasConceptScore W3100804201C199360897 @default.
- W3100804201 hasConceptScore W3100804201C2776434776 @default.
- W3100804201 hasConceptScore W3100804201C33923547 @default.
- W3100804201 hasConceptScore W3100804201C36503486 @default.
- W3100804201 hasConceptScore W3100804201C37736160 @default.
- W3100804201 hasConceptScore W3100804201C41008148 @default.
- W3100804201 hasConceptScore W3100804201C42357961 @default.