FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361852783> ?p ?o ?g. }

• W4361852783 endingPage "2032" @default.
• W4361852783 startingPage "2017" @default.
• W4361852783 abstract "As a branch of transfer learning, domain adaptation leverages useful knowledge from a source domain to a target domain for solving target tasks. Most of the existing domain adaptation methods focus on how to diminish the conditional distribution shift and learn invariant features between different domains. However, two important factors are overlooked by most existing methods: 1) the transferred features should be not only domain invariant but also discriminative and correlated, and 2) negative transfer should be avoided as much as possible for the target tasks. To fully consider these factors in domain adaptation, we propose a guided discrimination and correlation subspace learning (GDCSL) method for cross-domain image classification. GDCSL considers the domain-invariant, category-discriminative, and correlation learning of data. Specifically, GDCSL introduces the discriminative information associated with the source and target data by minimizing the intraclass scatter and maximizing the interclass distance. By designing a new correlation term, GDCSL extracts the most correlated features from the source and target domains for image classification. The global structure of the data can be preserved in GDCSL because the target samples are represented by the source samples. To avoid negative transfer issues, we use a sample reweighting method to detect target samples with different confidence levels. A semi-supervised extension of GDCSL (Semi-GDCSL) is also proposed, and a novel label selection scheme is introduced to ensure the correction of the target pseudo-labels. Comprehensive and extensive experiments are conducted on several cross-domain data benchmarks. The experimental results verify the effectiveness of the proposed methods over state-of-the-art domain adaptation methods." @default.
• W4361852783 created "2023-04-05" @default.
• W4361852783 creator A5024981683 @default.
• W4361852783 creator A5032139219 @default.
• W4361852783 creator A5043352718 @default.
• W4361852783 creator A5083774648 @default.
• W4361852783 date "2023-01-01" @default.
• W4361852783 modified "2023-10-18" @default.
• W4361852783 title "Guided Discrimination and Correlation Subspace Learning for Domain Adaptation" @default.
• W4361852783 cites W1907621547 @default.
• W4361852783 cites W1910772337 @default.
• W4361852783 cites W2006793117 @default.
• W4361852783 cites W2057266281 @default.
• W4361852783 cites W2096943734 @default.
• W4361852783 cites W2115403315 @default.
• W4361852783 cites W2150600350 @default.
• W4361852783 cites W2162854380 @default.
• W4361852783 cites W2214409633 @default.
• W4361852783 cites W2283717164 @default.
• W4361852783 cites W2422697180 @default.
• W4361852783 cites W2517537544 @default.
• W4361852783 cites W2616287544 @default.
• W4361852783 cites W2627183927 @default.
• W4361852783 cites W2758584002 @default.
• W4361852783 cites W2765838470 @default.
• W4361852783 cites W2796679234 @default.
• W4361852783 cites W2798199013 @default.
• W4361852783 cites W2801477643 @default.
• W4361852783 cites W2803106019 @default.
• W4361852783 cites W2805760974 @default.
• W4361852783 cites W2890479120 @default.
• W4361852783 cites W2897493810 @default.
• W4361852783 cites W2914951395 @default.
• W4361852783 cites W2923769473 @default.
• W4361852783 cites W2939571759 @default.
• W4361852783 cites W2948069880 @default.
• W4361852783 cites W2955547856 @default.
• W4361852783 cites W2962687275 @default.
• W4361852783 cites W2962986791 @default.
• W4361852783 cites W2963240485 @default.
• W4361852783 cites W2963532621 @default.
• W4361852783 cites W2963693396 @default.
• W4361852783 cites W2964109570 @default.
• W4361852783 cites W2964285681 @default.
• W4361852783 cites W2973077827 @default.
• W4361852783 cites W2979509742 @default.
• W4361852783 cites W2985836869 @default.
• W4361852783 cites W2988231818 @default.
• W4361852783 cites W2992062578 @default.
• W4361852783 cites W2997151494 @default.
• W4361852783 cites W2999216888 @default.
• W4361852783 cites W3009072794 @default.
• W4361852783 cites W3014788410 @default.
• W4361852783 cites W3018638193 @default.
• W4361852783 cites W3021632667 @default.
• W4361852783 cites W3025961898 @default.
• W4361852783 cites W3035576098 @default.
• W4361852783 cites W3041700978 @default.
• W4361852783 cites W3094117011 @default.
• W4361852783 cites W3099887033 @default.
• W4361852783 cites W3101679636 @default.
• W4361852783 cites W3109093849 @default.
• W4361852783 cites W3112846941 @default.
• W4361852783 cites W3119686825 @default.
• W4361852783 cites W3131415659 @default.
• W4361852783 cites W3134705486 @default.
• W4361852783 cites W3153166695 @default.
• W4361852783 cites W3159770254 @default.
• W4361852783 cites W3180960962 @default.
• W4361852783 cites W3197393979 @default.
• W4361852783 cites W3198731329 @default.
• W4361852783 cites W4210702020 @default.
• W4361852783 cites W4210923626 @default.
• W4361852783 cites W4224080302 @default.
• W4361852783 cites W4225668611 @default.
• W4361852783 cites W4292976134 @default.
• W4361852783 cites W4308686330 @default.
• W4361852783 doi "https://doi.org/10.1109/tip.2023.3261758" @default.
• W4361852783 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37018080" @default.
• W4361852783 hasPublicationYear "2023" @default.
• W4361852783 type Work @default.
• W4361852783 citedByCount "6" @default.
• W4361852783 countsByYear W43618527832023 @default.
• W4361852783 crossrefType "journal-article" @default.
• W4361852783 hasAuthorship W4361852783A5024981683 @default.
• W4361852783 hasAuthorship W4361852783A5032139219 @default.
• W4361852783 hasAuthorship W4361852783A5043352718 @default.
• W4361852783 hasAuthorship W4361852783A5083774648 @default.
• W4361852783 hasConcept C105795698 @default.
• W4361852783 hasConcept C117220453 @default.
• W4361852783 hasConcept C119857082 @default.
• W4361852783 hasConcept C150899416 @default.
• W4361852783 hasConcept C153180895 @default.
• W4361852783 hasConcept C154945302 @default.
• W4361852783 hasConcept C190470478 @default.
• W4361852783 hasConcept C2524010 @default.
• W4361852783 hasConcept C2776434776 @default.
• W4361852783 hasConcept C32834561 @default.

• next