Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387185337> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4387185337 abstract "Domain generalization (DG), which aims to learn a model that can generalize to an unseen target domain, has recently attracted increasing research interest. A major approach is to learn domain invariant representations to avoid greedily capturing all the correlations found in source domains caused by empirical risk minimization. Nevertheless, overly emphasizing learning of domain invariant representations might lead to learning overly-compressed domain invariant representations, causing confusion of different classes in a same domain. To address this limitation, we introduce a novel dynamic domain-weighted contrastive loss, which maximizes the subdomain differences between different classes especially those belonging to the same domain, while minimizing the average distance between the points of the convex hull of the aligned source domains. We propose Multi-source domain-adversarial generalization via dynamic domain-weighted Contrastive transfer learning (MsCtrl), a novel domain-adversarial generalization framework, which optimizes the distribution alignment of source and potential target subdomains in an adversarial manner under the “control” of the aforementioned contrastive loss. Extensive experiments based on real-world datasets demonstrate significant advantages of MsCtrl over existing state-of-the-art methods." @default.
- W4387185337 created "2023-09-30" @default.
- W4387185337 creator A5008558592 @default.
- W4387185337 creator A5011402708 @default.
- W4387185337 creator A5025156540 @default.
- W4387185337 creator A5048871276 @default.
- W4387185337 creator A5062013169 @default.
- W4387185337 creator A5064069283 @default.
- W4387185337 date "2023-09-28" @default.
- W4387185337 modified "2023-09-30" @default.
- W4387185337 title "Letting Go of Self-Domain Awareness: Multi-Source Domain-Adversarial Generalization via Dynamic Domain-Weighted Contrastive Transfer Learning" @default.
- W4387185337 doi "https://doi.org/10.3233/faia230450" @default.
- W4387185337 hasPublicationYear "2023" @default.
- W4387185337 type Work @default.
- W4387185337 citedByCount "0" @default.
- W4387185337 crossrefType "book-chapter" @default.
- W4387185337 hasAuthorship W4387185337A5008558592 @default.
- W4387185337 hasAuthorship W4387185337A5011402708 @default.
- W4387185337 hasAuthorship W4387185337A5025156540 @default.
- W4387185337 hasAuthorship W4387185337A5048871276 @default.
- W4387185337 hasAuthorship W4387185337A5062013169 @default.
- W4387185337 hasAuthorship W4387185337A5064069283 @default.
- W4387185337 hasBestOaLocation W43871853371 @default.
- W4387185337 hasConcept C11413529 @default.
- W4387185337 hasConcept C134306372 @default.
- W4387185337 hasConcept C150899416 @default.
- W4387185337 hasConcept C154945302 @default.
- W4387185337 hasConcept C177148314 @default.
- W4387185337 hasConcept C190470478 @default.
- W4387185337 hasConcept C33923547 @default.
- W4387185337 hasConcept C36503486 @default.
- W4387185337 hasConcept C37736160 @default.
- W4387185337 hasConcept C37914503 @default.
- W4387185337 hasConcept C41008148 @default.
- W4387185337 hasConcept C80444323 @default.
- W4387185337 hasConceptScore W4387185337C11413529 @default.
- W4387185337 hasConceptScore W4387185337C134306372 @default.
- W4387185337 hasConceptScore W4387185337C150899416 @default.
- W4387185337 hasConceptScore W4387185337C154945302 @default.
- W4387185337 hasConceptScore W4387185337C177148314 @default.
- W4387185337 hasConceptScore W4387185337C190470478 @default.
- W4387185337 hasConceptScore W4387185337C33923547 @default.
- W4387185337 hasConceptScore W4387185337C36503486 @default.
- W4387185337 hasConceptScore W4387185337C37736160 @default.
- W4387185337 hasConceptScore W4387185337C37914503 @default.
- W4387185337 hasConceptScore W4387185337C41008148 @default.
- W4387185337 hasConceptScore W4387185337C80444323 @default.
- W4387185337 hasLocation W43871853371 @default.
- W4387185337 hasOpenAccess W4387185337 @default.
- W4387185337 hasPrimaryLocation W43871853371 @default.
- W4387185337 hasRelatedWork W10944326 @default.
- W4387185337 hasRelatedWork W2901368259 @default.
- W4387185337 hasRelatedWork W2903917280 @default.
- W4387185337 hasRelatedWork W3089674223 @default.
- W4387185337 hasRelatedWork W3216881825 @default.
- W4387185337 hasRelatedWork W4205705013 @default.
- W4387185337 hasRelatedWork W4220812973 @default.
- W4387185337 hasRelatedWork W4226048313 @default.
- W4387185337 hasRelatedWork W4285606245 @default.
- W4387185337 hasRelatedWork W4308482295 @default.
- W4387185337 isParatext "false" @default.
- W4387185337 isRetracted "false" @default.
- W4387185337 workType "book-chapter" @default.