Matches in SemOpenAlex for { <https://semopenalex.org/work/W3022379890> ?p ?o ?g. }
- W3022379890 endingPage "105962" @default.
- W3022379890 startingPage "105962" @default.
- W3022379890 abstract "Current unsupervised domain adaptation (UDA) methods based on GAN (Generative Adversarial Network) architectures assume that source samples arise from a single distribution. These methods have shown compelling results by finding the transformation between source and target domains to reduce the distribution divergence. However, the one-to-one assumption renders the existing GAN-based UDA methods ineffective in a more realistic scenario that source samples are typically collected from diverse sources. In this paper, we present a novel GAN-enabled framework, which we call Multi-Source Adaptation Network (MSAN), for multiple-source domain adaptation (MDA) to mitigate the domain shifts between multiple source domains and the target domain. The proposed framework consists of multiple GAN architectures to learn bidirectional transformations between the source domains and the target domain efficiently and simultaneously. Technically, we introduce a joint feature space to guide the multi-level consistency constraints across all the transformations, in order to preserve the domain-invariant pattern and endow the discriminative power for the unlabeled target samples simultaneously during the adaptation. Moreover, the proposed model can naturally be used to enlarge the target dataset by utilizing the synthetic target images (with ground-truth labels from different source domains) and the pseudo-labeled target images, thereby allowing constructing the target-specific classifier in an unsupervised manner. Experiments demonstrate that our models exceed state-of-the-art results for MDA tasks on several benchmark datasets." @default.
- W3022379890 created "2020-05-13" @default.
- W3022379890 creator A5007280855 @default.
- W3022379890 creator A5052820597 @default.
- W3022379890 creator A5064262164 @default.
- W3022379890 creator A5082792246 @default.
- W3022379890 creator A5085129889 @default.
- W3022379890 date "2020-07-01" @default.
- W3022379890 modified "2023-10-15" @default.
- W3022379890 title "Multiple-source domain adaptation with generative adversarial nets" @default.
- W3022379890 cites W2023443487 @default.
- W3022379890 cites W2104094955 @default.
- W3022379890 cites W2112796928 @default.
- W3022379890 cites W2133556223 @default.
- W3022379890 cites W2165698076 @default.
- W3022379890 cites W2605488490 @default.
- W3022379890 cites W2617027347 @default.
- W3022379890 cites W2798453135 @default.
- W3022379890 cites W2798681837 @default.
- W3022379890 cites W2804750607 @default.
- W3022379890 cites W2890418037 @default.
- W3022379890 cites W2916681389 @default.
- W3022379890 cites W2962793481 @default.
- W3022379890 cites W2963073614 @default.
- W3022379890 cites W2963240485 @default.
- W3022379890 cites W2963506806 @default.
- W3022379890 cites W2984221099 @default.
- W3022379890 doi "https://doi.org/10.1016/j.knosys.2020.105962" @default.
- W3022379890 hasPublicationYear "2020" @default.
- W3022379890 type Work @default.
- W3022379890 sameAs 3022379890 @default.
- W3022379890 citedByCount "21" @default.
- W3022379890 countsByYear W30223798902020 @default.
- W3022379890 countsByYear W30223798902021 @default.
- W3022379890 countsByYear W30223798902022 @default.
- W3022379890 countsByYear W30223798902023 @default.
- W3022379890 crossrefType "journal-article" @default.
- W3022379890 hasAuthorship W3022379890A5007280855 @default.
- W3022379890 hasAuthorship W3022379890A5052820597 @default.
- W3022379890 hasAuthorship W3022379890A5064262164 @default.
- W3022379890 hasAuthorship W3022379890A5082792246 @default.
- W3022379890 hasAuthorship W3022379890A5085129889 @default.
- W3022379890 hasConcept C104317684 @default.
- W3022379890 hasConcept C111919701 @default.
- W3022379890 hasConcept C119857082 @default.
- W3022379890 hasConcept C13280743 @default.
- W3022379890 hasConcept C134306372 @default.
- W3022379890 hasConcept C138885662 @default.
- W3022379890 hasConcept C153180895 @default.
- W3022379890 hasConcept C154945302 @default.
- W3022379890 hasConcept C185592680 @default.
- W3022379890 hasConcept C185798385 @default.
- W3022379890 hasConcept C204241405 @default.
- W3022379890 hasConcept C205649164 @default.
- W3022379890 hasConcept C207390915 @default.
- W3022379890 hasConcept C2776434776 @default.
- W3022379890 hasConcept C33923547 @default.
- W3022379890 hasConcept C36503486 @default.
- W3022379890 hasConcept C41008148 @default.
- W3022379890 hasConcept C41895202 @default.
- W3022379890 hasConcept C43126263 @default.
- W3022379890 hasConcept C55493867 @default.
- W3022379890 hasConcept C95623464 @default.
- W3022379890 hasConcept C97931131 @default.
- W3022379890 hasConceptScore W3022379890C104317684 @default.
- W3022379890 hasConceptScore W3022379890C111919701 @default.
- W3022379890 hasConceptScore W3022379890C119857082 @default.
- W3022379890 hasConceptScore W3022379890C13280743 @default.
- W3022379890 hasConceptScore W3022379890C134306372 @default.
- W3022379890 hasConceptScore W3022379890C138885662 @default.
- W3022379890 hasConceptScore W3022379890C153180895 @default.
- W3022379890 hasConceptScore W3022379890C154945302 @default.
- W3022379890 hasConceptScore W3022379890C185592680 @default.
- W3022379890 hasConceptScore W3022379890C185798385 @default.
- W3022379890 hasConceptScore W3022379890C204241405 @default.
- W3022379890 hasConceptScore W3022379890C205649164 @default.
- W3022379890 hasConceptScore W3022379890C207390915 @default.
- W3022379890 hasConceptScore W3022379890C2776434776 @default.
- W3022379890 hasConceptScore W3022379890C33923547 @default.
- W3022379890 hasConceptScore W3022379890C36503486 @default.
- W3022379890 hasConceptScore W3022379890C41008148 @default.
- W3022379890 hasConceptScore W3022379890C41895202 @default.
- W3022379890 hasConceptScore W3022379890C43126263 @default.
- W3022379890 hasConceptScore W3022379890C55493867 @default.
- W3022379890 hasConceptScore W3022379890C95623464 @default.
- W3022379890 hasConceptScore W3022379890C97931131 @default.
- W3022379890 hasFunder F4320321001 @default.
- W3022379890 hasFunder F4320335787 @default.
- W3022379890 hasLocation W30223798901 @default.
- W3022379890 hasOpenAccess W3022379890 @default.
- W3022379890 hasPrimaryLocation W30223798901 @default.
- W3022379890 hasRelatedWork W2024160000 @default.
- W3022379890 hasRelatedWork W2061273563 @default.
- W3022379890 hasRelatedWork W2285052147 @default.
- W3022379890 hasRelatedWork W2729514902 @default.
- W3022379890 hasRelatedWork W2773500201 @default.
- W3022379890 hasRelatedWork W2929309436 @default.
- W3022379890 hasRelatedWork W3080655457 @default.