Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313377937> ?p ?o ?g. }
- W4313377937 endingPage "87" @default.
- W4313377937 startingPage "72" @default.
- W4313377937 abstract "Feature-based domain adaptation methods project samples from different domains into the same feature space and try to align the distribution of two domains to learn an effective transferable model. The vital problem is how to find a proper way to reduce the domain shift and improve the discriminability of features. To address the above issues, we propose a unified Probability-based Graph embedding Cross-domain and class Discriminative feature learning framework for unsupervised domain adaptation (PGCD). Specifically, we propose novel graph embedding structures to be the class discriminative transfer feature learning item and cross-domain alignment item, which can make the same-category samples compact in each domain, and fully align the local and global geometric structure across domains. Besides, two theoretical analyses are given to prove the interpretability of the proposed graph structures, which can further describe the relationships between samples to samples in single-domain and cross-domain transfer feature learning scenarios. Moreover, we adopt novel weight strategies via probability information to generate robust centroids in each proposed item to enhance the accuracy of transfer feature learning and reduce the error accumulation. Compared with the advanced approaches by comprehensive experiments, the promising performance on the benchmark datasets verify the effectiveness of the proposed model." @default.
- W4313377937 created "2023-01-06" @default.
- W4313377937 creator A5003387396 @default.
- W4313377937 creator A5008289463 @default.
- W4313377937 creator A5037846785 @default.
- W4313377937 creator A5050084697 @default.
- W4313377937 creator A5077723657 @default.
- W4313377937 date "2023-01-01" @default.
- W4313377937 modified "2023-10-01" @default.
- W4313377937 title "Probability-Based Graph Embedding Cross-Domain and Class Discriminative Feature Learning for Domain Adaptation" @default.
- W4313377937 cites W1985697265 @default.
- W4313377937 cites W2096943734 @default.
- W4313377937 cites W2115403315 @default.
- W4313377937 cites W2120149881 @default.
- W4313377937 cites W2159570078 @default.
- W4313377937 cites W2165698076 @default.
- W4313377937 cites W2194775991 @default.
- W4313377937 cites W2240559667 @default.
- W4313377937 cites W2552765257 @default.
- W4313377937 cites W2616287544 @default.
- W4313377937 cites W2767179670 @default.
- W4313377937 cites W2789767547 @default.
- W4313377937 cites W2800222246 @default.
- W4313377937 cites W2801443642 @default.
- W4313377937 cites W2801477643 @default.
- W4313377937 cites W2803106019 @default.
- W4313377937 cites W2884771968 @default.
- W4313377937 cites W2888000811 @default.
- W4313377937 cites W2963519194 @default.
- W4313377937 cites W2964288524 @default.
- W4313377937 cites W2965604235 @default.
- W4313377937 cites W2966588426 @default.
- W4313377937 cites W2990462091 @default.
- W4313377937 cites W2997739323 @default.
- W4313377937 cites W2998807071 @default.
- W4313377937 cites W2999216888 @default.
- W4313377937 cites W3009072794 @default.
- W4313377937 cites W3033022871 @default.
- W4313377937 cites W3034324233 @default.
- W4313377937 cites W3034591020 @default.
- W4313377937 cites W3034738317 @default.
- W4313377937 cites W3035146858 @default.
- W4313377937 cites W3035519852 @default.
- W4313377937 cites W3049560862 @default.
- W4313377937 cites W3084561752 @default.
- W4313377937 cites W3094117011 @default.
- W4313377937 cites W3125003080 @default.
- W4313377937 cites W3127196078 @default.
- W4313377937 cites W3154061064 @default.
- W4313377937 cites W3159770254 @default.
- W4313377937 cites W3166635318 @default.
- W4313377937 cites W3176602994 @default.
- W4313377937 cites W3203816763 @default.
- W4313377937 doi "https://doi.org/10.1109/tip.2022.3226405" @default.
- W4313377937 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37015526" @default.
- W4313377937 hasPublicationYear "2023" @default.
- W4313377937 type Work @default.
- W4313377937 citedByCount "2" @default.
- W4313377937 countsByYear W43133779372023 @default.
- W4313377937 crossrefType "journal-article" @default.
- W4313377937 hasAuthorship W4313377937A5003387396 @default.
- W4313377937 hasAuthorship W4313377937A5008289463 @default.
- W4313377937 hasAuthorship W4313377937A5037846785 @default.
- W4313377937 hasAuthorship W4313377937A5050084697 @default.
- W4313377937 hasAuthorship W4313377937A5077723657 @default.
- W4313377937 hasConcept C105795698 @default.
- W4313377937 hasConcept C119857082 @default.
- W4313377937 hasConcept C132525143 @default.
- W4313377937 hasConcept C134306372 @default.
- W4313377937 hasConcept C138885662 @default.
- W4313377937 hasConcept C146599234 @default.
- W4313377937 hasConcept C149441793 @default.
- W4313377937 hasConcept C150899416 @default.
- W4313377937 hasConcept C153180895 @default.
- W4313377937 hasConcept C154945302 @default.
- W4313377937 hasConcept C2776401178 @default.
- W4313377937 hasConcept C2781067378 @default.
- W4313377937 hasConcept C33923547 @default.
- W4313377937 hasConcept C36503486 @default.
- W4313377937 hasConcept C41008148 @default.
- W4313377937 hasConcept C41608201 @default.
- W4313377937 hasConcept C41895202 @default.
- W4313377937 hasConcept C59404180 @default.
- W4313377937 hasConcept C80444323 @default.
- W4313377937 hasConcept C83665646 @default.
- W4313377937 hasConcept C97931131 @default.
- W4313377937 hasConceptScore W4313377937C105795698 @default.
- W4313377937 hasConceptScore W4313377937C119857082 @default.
- W4313377937 hasConceptScore W4313377937C132525143 @default.
- W4313377937 hasConceptScore W4313377937C134306372 @default.
- W4313377937 hasConceptScore W4313377937C138885662 @default.
- W4313377937 hasConceptScore W4313377937C146599234 @default.
- W4313377937 hasConceptScore W4313377937C149441793 @default.
- W4313377937 hasConceptScore W4313377937C150899416 @default.
- W4313377937 hasConceptScore W4313377937C153180895 @default.
- W4313377937 hasConceptScore W4313377937C154945302 @default.
- W4313377937 hasConceptScore W4313377937C2776401178 @default.
- W4313377937 hasConceptScore W4313377937C2781067378 @default.