FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4213084105> ?p ?o ?g. }

• W4213084105 endingPage "5494" @default.
• W4213084105 startingPage "5481" @default.
• W4213084105 abstract "Unsupervised domain adaptation aims to leverage knowledge from a labeled source domain to learn an accurate model in an unlabeled target domain. However, many previous approaches propose to learn domain agnostic feature representations using a global distribution alignment objective, which does not consider the fine-grained cluster structures in the source and target domains. As such, the goal of this paper is to address two challenging problems: <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1) how to thoroughly explore fine-grained cluster structure knowledge in the source and target domains, 2) how to effectively incorporate these structure knowledge for adaptation.</i> Regarding the first point, we are motivated by structural domain similarity assumption and propose structural representation learning, which is achieved by enforcing structural consistency between the source and target domains while retaining their individual discriminative properties. Regarding the second point, we firstly devise a novel structural centroid-based label prediction method, which explicitly models structural representations to form discriminative source and target cluster centroids, and estimates the label distribution of each target sample through the cosine similarity between its corresponding target cluster centroid and all the other source cluster centroids. Then, we adopt clustering learning to incorporate these discriminative structure knowledge for adaptation by minimizing the KL divergence between the predictive target label distribution and an introduced auxiliary one. Comprehensive experiments and analyses on four benchmark datasets demonstrate the superiority of the proposed discriminative clustering framework." @default.
• W4213084105 created "2022-02-24" @default.
• W4213084105 creator A5002944447 @default.
• W4213084105 creator A5006111233 @default.
• W4213084105 creator A5048763159 @default.
• W4213084105 creator A5050817770 @default.
• W4213084105 creator A5060755096 @default.
• W4213084105 date "2022-08-01" @default.
• W4213084105 modified "2023-10-17" @default.
• W4213084105 title "Exploring Fine-Grained Cluster Structure Knowledge for Unsupervised Domain Adaptation" @default.
• W4213084105 cites W1972702299 @default.
• W4213084105 cites W2057266281 @default.
• W4213084105 cites W2104094955 @default.
• W4213084105 cites W2108598243 @default.
• W4213084105 cites W2115403315 @default.
• W4213084105 cites W2138621090 @default.
• W4213084105 cites W2150593711 @default.
• W4213084105 cites W2157032359 @default.
• W4213084105 cites W2165698076 @default.
• W4213084105 cites W2194775991 @default.
• W4213084105 cites W2328765253 @default.
• W4213084105 cites W2593768305 @default.
• W4213084105 cites W2608862709 @default.
• W4213084105 cites W2616287544 @default.
• W4213084105 cites W2627183927 @default.
• W4213084105 cites W2770645414 @default.
• W4213084105 cites W2805548989 @default.
• W4213084105 cites W2805760974 @default.
• W4213084105 cites W2883725317 @default.
• W4213084105 cites W2896016251 @default.
• W4213084105 cites W2897536120 @default.
• W4213084105 cites W2954628187 @default.
• W4213084105 cites W2957037461 @default.
• W4213084105 cites W2962687275 @default.
• W4213084105 cites W2963468416 @default.
• W4213084105 cites W2963532621 @default.
• W4213084105 cites W2964285681 @default.
• W4213084105 cites W2965898445 @default.
• W4213084105 cites W2979920800 @default.
• W4213084105 cites W2991405316 @default.
• W4213084105 cites W2996787432 @default.
• W4213084105 cites W2997189783 @default.
• W4213084105 cites W2997654197 @default.
• W4213084105 cites W2998125392 @default.
• W4213084105 cites W2998273021 @default.
• W4213084105 cites W3002879391 @default.
• W4213084105 cites W3007744269 @default.
• W4213084105 cites W3009238880 @default.
• W4213084105 cites W3034324233 @default.
• W4213084105 cites W3034335103 @default.
• W4213084105 cites W3034591020 @default.
• W4213084105 cites W3034738317 @default.
• W4213084105 cites W3035456997 @default.
• W4213084105 cites W3035519852 @default.
• W4213084105 cites W3035576098 @default.
• W4213084105 cites W3047377799 @default.
• W4213084105 cites W3095697905 @default.
• W4213084105 cites W3135748285 @default.
• W4213084105 cites W3160639636 @default.
• W4213084105 cites W3166529525 @default.
• W4213084105 cites W3175294391 @default.
• W4213084105 cites W3206154535 @default.
• W4213084105 cites W4149471 @default.
• W4213084105 doi "https://doi.org/10.1109/tcsvt.2022.3151387" @default.
• W4213084105 hasPublicationYear "2022" @default.
• W4213084105 type Work @default.
• W4213084105 citedByCount "6" @default.
• W4213084105 countsByYear W42130841052022 @default.
• W4213084105 countsByYear W42130841052023 @default.
• W4213084105 crossrefType "journal-article" @default.
• W4213084105 hasAuthorship W4213084105A5002944447 @default.
• W4213084105 hasAuthorship W4213084105A5006111233 @default.
• W4213084105 hasAuthorship W4213084105A5048763159 @default.
• W4213084105 hasAuthorship W4213084105A5050817770 @default.
• W4213084105 hasAuthorship W4213084105A5060755096 @default.
• W4213084105 hasConcept C103278499 @default.
• W4213084105 hasConcept C115961682 @default.
• W4213084105 hasConcept C119857082 @default.
• W4213084105 hasConcept C124101348 @default.
• W4213084105 hasConcept C134306372 @default.
• W4213084105 hasConcept C146599234 @default.
• W4213084105 hasConcept C153083717 @default.
• W4213084105 hasConcept C153180895 @default.
• W4213084105 hasConcept C154945302 @default.
• W4213084105 hasConcept C2780762811 @default.
• W4213084105 hasConcept C33923547 @default.
• W4213084105 hasConcept C36503486 @default.
• W4213084105 hasConcept C41008148 @default.
• W4213084105 hasConcept C59404180 @default.
• W4213084105 hasConcept C73555534 @default.
• W4213084105 hasConcept C97931131 @default.
• W4213084105 hasConceptScore W4213084105C103278499 @default.
• W4213084105 hasConceptScore W4213084105C115961682 @default.
• W4213084105 hasConceptScore W4213084105C119857082 @default.
• W4213084105 hasConceptScore W4213084105C124101348 @default.
• W4213084105 hasConceptScore W4213084105C134306372 @default.
• W4213084105 hasConceptScore W4213084105C146599234 @default.
• W4213084105 hasConceptScore W4213084105C153083717 @default.

• next