Matches in SemOpenAlex for { <https://semopenalex.org/work/W2341914330> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2341914330 endingPage "2040" @default.
- W2341914330 startingPage "2027" @default.
- W2341914330 abstract "Domain adaptation generalizes a learning model across source domain and target domain that are sampled from different distributions. It is widely applied to cross-domain data mining for reusing labeled information and mitigating labeling consumption. Recent studies reveal that deep neural networks can learn abstract feature representation, which can reduce, but not remove, the cross-domain discrepancy. To enhance the invariance of deep representation and make it more transferable across domains, we propose a unified deep adaptation framework for jointly learning transferable representation and classifier to enable scalable domain adaptation, by taking the advantages of both deep learning and optimal two-sample matching. The framework constitutes two inter-dependent paradigms, unsupervised pre-training for effective training of deep models using deep denoising autoencoders, and supervised fine-tuning for effective exploitation of discriminative information using deep neural networks, both learned by embedding the deep representations to reproducing kernel Hilbert spaces (RKHSs) and optimally matching different domain distributions. To enable scalable learning, we develop a linear-time algorithm using unbiased estimate that scales linearly to large samples. Extensive empirical results show that the proposed framework significantly outperforms state of the art methods on diverse adaptation tasks: sentiment polarity prediction, email spam filtering, newsgroup content categorization, and visual object recognition." @default.
- W2341914330 created "2016-06-24" @default.
- W2341914330 creator A5019241553 @default.
- W2341914330 creator A5028650738 @default.
- W2341914330 creator A5034579434 @default.
- W2341914330 creator A5036357902 @default.
- W2341914330 creator A5068911982 @default.
- W2341914330 date "2016-08-01" @default.
- W2341914330 modified "2023-10-13" @default.
- W2341914330 title "Deep Learning of Transferable Representation for Scalable Domain Adaptation" @default.
- W2341914330 cites W1722318740 @default.
- W2341914330 cites W1779010541 @default.
- W2341914330 cites W1981658663 @default.
- W2341914330 cites W2087977130 @default.
- W2341914330 cites W2096943734 @default.
- W2341914330 cites W2100495367 @default.
- W2341914330 cites W2100664256 @default.
- W2341914330 cites W2104094955 @default.
- W2341914330 cites W2115403315 @default.
- W2341914330 cites W2120149881 @default.
- W2341914330 cites W2127201730 @default.
- W2341914330 cites W2153353890 @default.
- W2341914330 cites W2163922914 @default.
- W2341914330 cites W2165698076 @default.
- W2341914330 doi "https://doi.org/10.1109/tkde.2016.2554549" @default.
- W2341914330 hasPublicationYear "2016" @default.
- W2341914330 type Work @default.
- W2341914330 sameAs 2341914330 @default.
- W2341914330 citedByCount "142" @default.
- W2341914330 countsByYear W23419143302016 @default.
- W2341914330 countsByYear W23419143302017 @default.
- W2341914330 countsByYear W23419143302018 @default.
- W2341914330 countsByYear W23419143302019 @default.
- W2341914330 countsByYear W23419143302020 @default.
- W2341914330 countsByYear W23419143302021 @default.
- W2341914330 countsByYear W23419143302022 @default.
- W2341914330 countsByYear W23419143302023 @default.
- W2341914330 crossrefType "journal-article" @default.
- W2341914330 hasAuthorship W2341914330A5019241553 @default.
- W2341914330 hasAuthorship W2341914330A5028650738 @default.
- W2341914330 hasAuthorship W2341914330A5034579434 @default.
- W2341914330 hasAuthorship W2341914330A5036357902 @default.
- W2341914330 hasAuthorship W2341914330A5068911982 @default.
- W2341914330 hasConcept C108583219 @default.
- W2341914330 hasConcept C119857082 @default.
- W2341914330 hasConcept C153180895 @default.
- W2341914330 hasConcept C154945302 @default.
- W2341914330 hasConcept C2776434776 @default.
- W2341914330 hasConcept C41008148 @default.
- W2341914330 hasConcept C48044578 @default.
- W2341914330 hasConcept C59404180 @default.
- W2341914330 hasConcept C77088390 @default.
- W2341914330 hasConcept C95623464 @default.
- W2341914330 hasConcept C97931131 @default.
- W2341914330 hasConceptScore W2341914330C108583219 @default.
- W2341914330 hasConceptScore W2341914330C119857082 @default.
- W2341914330 hasConceptScore W2341914330C153180895 @default.
- W2341914330 hasConceptScore W2341914330C154945302 @default.
- W2341914330 hasConceptScore W2341914330C2776434776 @default.
- W2341914330 hasConceptScore W2341914330C41008148 @default.
- W2341914330 hasConceptScore W2341914330C48044578 @default.
- W2341914330 hasConceptScore W2341914330C59404180 @default.
- W2341914330 hasConceptScore W2341914330C77088390 @default.
- W2341914330 hasConceptScore W2341914330C95623464 @default.
- W2341914330 hasConceptScore W2341914330C97931131 @default.
- W2341914330 hasFunder F4320306076 @default.
- W2341914330 hasFunder F4320321001 @default.
- W2341914330 hasFunder F4320321543 @default.
- W2341914330 hasIssue "8" @default.
- W2341914330 hasLocation W23419143301 @default.
- W2341914330 hasOpenAccess W2341914330 @default.
- W2341914330 hasPrimaryLocation W23419143301 @default.
- W2341914330 hasRelatedWork W2740361506 @default.
- W2341914330 hasRelatedWork W3008648540 @default.
- W2341914330 hasRelatedWork W3080655457 @default.
- W2341914330 hasRelatedWork W3136267388 @default.
- W2341914330 hasRelatedWork W3166286441 @default.
- W2341914330 hasRelatedWork W3186065094 @default.
- W2341914330 hasRelatedWork W3204418343 @default.
- W2341914330 hasRelatedWork W3214142563 @default.
- W2341914330 hasRelatedWork W4287263085 @default.
- W2341914330 hasRelatedWork W4312246223 @default.
- W2341914330 hasVolume "28" @default.
- W2341914330 isParatext "false" @default.
- W2341914330 isRetracted "false" @default.
- W2341914330 magId "2341914330" @default.
- W2341914330 workType "article" @default.