Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286588250> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4286588250 abstract "With various face presentation attacks emerging continually, face anti-spoofing (FAS) approaches based on domain generalization (DG) have drawn growing attention. Existing DG-based FAS approaches always capture the domain-invariant features for generalizing on the various unseen domains. However, they neglect individual source domains' discriminative characteristics and diverse domain-specific information of the unseen domains, and the trained model is not sufficient to be adapted to various unseen domains. To address this issue, we propose an Adaptive Mixture of Experts Learning (AMEL) framework, which exploits the domain-specific information to adaptively establish the link among the seen source domains and unseen target domains to further improve the generalization. Concretely, Domain-Specific Experts (DSE) are designed to investigate discriminative and unique domain-specific features as a complement to common domain-invariant features. Moreover, Dynamic Expert Aggregation (DEA) is proposed to adaptively aggregate the complementary information of each source expert based on the domain relevance to the unseen target domain. And combined with meta-learning, these modules work collaboratively to adaptively aggregate meaningful domain-specific information for the various unseen target domains. Extensive experiments and visualizations demonstrate the effectiveness of our method against the state-of-the-art competitors." @default.
- W4286588250 created "2022-07-22" @default.
- W4286588250 creator A5031210225 @default.
- W4286588250 creator A5033773467 @default.
- W4286588250 creator A5054879013 @default.
- W4286588250 creator A5084218062 @default.
- W4286588250 creator A5086397952 @default.
- W4286588250 creator A5090731421 @default.
- W4286588250 date "2022-07-20" @default.
- W4286588250 modified "2023-09-28" @default.
- W4286588250 title "Adaptive Mixture of Experts Learning for Generalizable Face Anti-Spoofing" @default.
- W4286588250 doi "https://doi.org/10.48550/arxiv.2207.09868" @default.
- W4286588250 hasPublicationYear "2022" @default.
- W4286588250 type Work @default.
- W4286588250 citedByCount "0" @default.
- W4286588250 crossrefType "posted-content" @default.
- W4286588250 hasAuthorship W4286588250A5031210225 @default.
- W4286588250 hasAuthorship W4286588250A5033773467 @default.
- W4286588250 hasAuthorship W4286588250A5054879013 @default.
- W4286588250 hasAuthorship W4286588250A5084218062 @default.
- W4286588250 hasAuthorship W4286588250A5086397952 @default.
- W4286588250 hasAuthorship W4286588250A5090731421 @default.
- W4286588250 hasBestOaLocation W42865882501 @default.
- W4286588250 hasConcept C104317684 @default.
- W4286588250 hasConcept C112313634 @default.
- W4286588250 hasConcept C119857082 @default.
- W4286588250 hasConcept C127716648 @default.
- W4286588250 hasConcept C134306372 @default.
- W4286588250 hasConcept C153180895 @default.
- W4286588250 hasConcept C154945302 @default.
- W4286588250 hasConcept C158154518 @default.
- W4286588250 hasConcept C165696696 @default.
- W4286588250 hasConcept C177148314 @default.
- W4286588250 hasConcept C17744445 @default.
- W4286588250 hasConcept C185592680 @default.
- W4286588250 hasConcept C188082640 @default.
- W4286588250 hasConcept C190470478 @default.
- W4286588250 hasConcept C199539241 @default.
- W4286588250 hasConcept C33923547 @default.
- W4286588250 hasConcept C36503486 @default.
- W4286588250 hasConcept C37914503 @default.
- W4286588250 hasConcept C38652104 @default.
- W4286588250 hasConcept C41008148 @default.
- W4286588250 hasConcept C55493867 @default.
- W4286588250 hasConcept C97931131 @default.
- W4286588250 hasConceptScore W4286588250C104317684 @default.
- W4286588250 hasConceptScore W4286588250C112313634 @default.
- W4286588250 hasConceptScore W4286588250C119857082 @default.
- W4286588250 hasConceptScore W4286588250C127716648 @default.
- W4286588250 hasConceptScore W4286588250C134306372 @default.
- W4286588250 hasConceptScore W4286588250C153180895 @default.
- W4286588250 hasConceptScore W4286588250C154945302 @default.
- W4286588250 hasConceptScore W4286588250C158154518 @default.
- W4286588250 hasConceptScore W4286588250C165696696 @default.
- W4286588250 hasConceptScore W4286588250C177148314 @default.
- W4286588250 hasConceptScore W4286588250C17744445 @default.
- W4286588250 hasConceptScore W4286588250C185592680 @default.
- W4286588250 hasConceptScore W4286588250C188082640 @default.
- W4286588250 hasConceptScore W4286588250C190470478 @default.
- W4286588250 hasConceptScore W4286588250C199539241 @default.
- W4286588250 hasConceptScore W4286588250C33923547 @default.
- W4286588250 hasConceptScore W4286588250C36503486 @default.
- W4286588250 hasConceptScore W4286588250C37914503 @default.
- W4286588250 hasConceptScore W4286588250C38652104 @default.
- W4286588250 hasConceptScore W4286588250C41008148 @default.
- W4286588250 hasConceptScore W4286588250C55493867 @default.
- W4286588250 hasConceptScore W4286588250C97931131 @default.
- W4286588250 hasLocation W42865882501 @default.
- W4286588250 hasOpenAccess W4286588250 @default.
- W4286588250 hasPrimaryLocation W42865882501 @default.
- W4286588250 hasRelatedWork W10944326 @default.
- W4286588250 hasRelatedWork W11658723 @default.
- W4286588250 hasRelatedWork W12783365 @default.
- W4286588250 hasRelatedWork W13121074 @default.
- W4286588250 hasRelatedWork W13188192 @default.
- W4286588250 hasRelatedWork W4649193 @default.
- W4286588250 hasRelatedWork W4703903 @default.
- W4286588250 hasRelatedWork W7072919 @default.
- W4286588250 hasRelatedWork W9565258 @default.
- W4286588250 hasRelatedWork W10597021 @default.
- W4286588250 isParatext "false" @default.
- W4286588250 isRetracted "false" @default.
- W4286588250 workType "article" @default.