Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312462776> ?p ?o ?g. }
- W4312462776 endingPage "241" @default.
- W4312462776 startingPage "223" @default.
- W4312462776 abstract "Domain adaptation (DA) aims to transfer knowledge learned from a labeled source domain to an unlabeled or a less labeled but related target domain. Ideally, the source and target distributions should be aligned to each other equally to achieve unbiased knowledge transfer. However, due to the significant imbalance between the amount of annotated data in the source and target domains, usually only the target distribution is aligned to the source domain, leading to adapting unnecessary source specific knowledge to the target domain, i.e., biased domain adaptation. To resolve this problem, in this work, we delve into the transferability estimation problem in domain adaptation and propose a non-intrusive Unbiased Transferability Estimation Plug-in (UTEP) by modeling the uncertainty of a discriminator in adversarial-based DA methods to optimize unbiased transfer. We theoretically analyze the effectiveness of the proposed approach to unbiased transferability learning in DA. Furthermore, to alleviate the impact of imbalanced annotated data, we utilize the estimated uncertainty for pseudo label selection of unlabeled samples in the target domain, which helps achieve better marginal and conditional distribution alignments between domains. Extensive experimental results on a high variety of DA benchmark datasets show that the proposed approach can be readily incorporated into various adversarial-based DA methods, achieving state-of-the-art performance." @default.
- W4312462776 created "2023-01-04" @default.
- W4312462776 creator A5029815331 @default.
- W4312462776 creator A5039302902 @default.
- W4312462776 creator A5080142285 @default.
- W4312462776 creator A5082901351 @default.
- W4312462776 creator A5084391120 @default.
- W4312462776 creator A5087158377 @default.
- W4312462776 date "2022-01-01" @default.
- W4312462776 modified "2023-09-27" @default.
- W4312462776 title "Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling" @default.
- W4312462776 cites W1594039573 @default.
- W4312462776 cites W1722318740 @default.
- W4312462776 cites W2042179218 @default.
- W4312462776 cites W2104094955 @default.
- W4312462776 cites W2111959010 @default.
- W4312462776 cites W2194775991 @default.
- W4312462776 cites W2593768305 @default.
- W4312462776 cites W2600230189 @default.
- W4312462776 cites W2904706552 @default.
- W4312462776 cites W2948959975 @default.
- W4312462776 cites W2962986791 @default.
- W4312462776 cites W2963240485 @default.
- W4312462776 cites W2963532621 @default.
- W4312462776 cites W2965604235 @default.
- W4312462776 cites W2965711922 @default.
- W4312462776 cites W2971220197 @default.
- W4312462776 cites W2978573218 @default.
- W4312462776 cites W2982204955 @default.
- W4312462776 cites W2986381065 @default.
- W4312462776 cites W2991482886 @default.
- W4312462776 cites W3018638193 @default.
- W4312462776 cites W3034324233 @default.
- W4312462776 cites W3035519852 @default.
- W4312462776 cites W3035576098 @default.
- W4312462776 cites W3106063055 @default.
- W4312462776 cites W3109093849 @default.
- W4312462776 cites W3119635706 @default.
- W4312462776 cites W3165113810 @default.
- W4312462776 cites W3172748299 @default.
- W4312462776 cites W3174389852 @default.
- W4312462776 cites W3176663948 @default.
- W4312462776 cites W3177151237 @default.
- W4312462776 cites W3181434681 @default.
- W4312462776 cites W3190654993 @default.
- W4312462776 cites W3194427711 @default.
- W4312462776 cites W3206005599 @default.
- W4312462776 doi "https://doi.org/10.1007/978-3-031-19821-2_13" @default.
- W4312462776 hasPublicationYear "2022" @default.
- W4312462776 type Work @default.
- W4312462776 citedByCount "1" @default.
- W4312462776 countsByYear W43124627762023 @default.
- W4312462776 crossrefType "book-chapter" @default.
- W4312462776 hasAuthorship W4312462776A5029815331 @default.
- W4312462776 hasAuthorship W4312462776A5039302902 @default.
- W4312462776 hasAuthorship W4312462776A5080142285 @default.
- W4312462776 hasAuthorship W4312462776A5082901351 @default.
- W4312462776 hasAuthorship W4312462776A5084391120 @default.
- W4312462776 hasAuthorship W4312462776A5087158377 @default.
- W4312462776 hasBestOaLocation W43124627762 @default.
- W4312462776 hasConcept C105795698 @default.
- W4312462776 hasConcept C119857082 @default.
- W4312462776 hasConcept C120665830 @default.
- W4312462776 hasConcept C121332964 @default.
- W4312462776 hasConcept C124101348 @default.
- W4312462776 hasConcept C13280743 @default.
- W4312462776 hasConcept C134306372 @default.
- W4312462776 hasConcept C139807058 @default.
- W4312462776 hasConcept C140331021 @default.
- W4312462776 hasConcept C150899416 @default.
- W4312462776 hasConcept C154945302 @default.
- W4312462776 hasConcept C185798385 @default.
- W4312462776 hasConcept C205649164 @default.
- W4312462776 hasConcept C2776434776 @default.
- W4312462776 hasConcept C2779803651 @default.
- W4312462776 hasConcept C2780665216 @default.
- W4312462776 hasConcept C33923547 @default.
- W4312462776 hasConcept C36503486 @default.
- W4312462776 hasConcept C41008148 @default.
- W4312462776 hasConcept C43555835 @default.
- W4312462776 hasConcept C61272859 @default.
- W4312462776 hasConcept C76155785 @default.
- W4312462776 hasConcept C94915269 @default.
- W4312462776 hasConcept C95623464 @default.
- W4312462776 hasConceptScore W4312462776C105795698 @default.
- W4312462776 hasConceptScore W4312462776C119857082 @default.
- W4312462776 hasConceptScore W4312462776C120665830 @default.
- W4312462776 hasConceptScore W4312462776C121332964 @default.
- W4312462776 hasConceptScore W4312462776C124101348 @default.
- W4312462776 hasConceptScore W4312462776C13280743 @default.
- W4312462776 hasConceptScore W4312462776C134306372 @default.
- W4312462776 hasConceptScore W4312462776C139807058 @default.
- W4312462776 hasConceptScore W4312462776C140331021 @default.
- W4312462776 hasConceptScore W4312462776C150899416 @default.
- W4312462776 hasConceptScore W4312462776C154945302 @default.
- W4312462776 hasConceptScore W4312462776C185798385 @default.
- W4312462776 hasConceptScore W4312462776C205649164 @default.
- W4312462776 hasConceptScore W4312462776C2776434776 @default.