FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3139628984> ?p ?o ?g. }

• W3139628984 abstract "Universal domain adaptation (UniDA) has been proposed to transfer knowledge learned from a label-rich source domain to a label-scarce target domain without any constraints on the label sets. In practice, however, it is difficult to obtain a large amount of perfectly clean labeled data in a source domain with limited resources. Existing UniDA methods rely on source samples with correct annotations, which greatly limits their application in the real world. Hence, we consider a new realistic setting called Noisy UniDA, in which classifiers are trained with noisy labeled data from the source domain and unlabeled data with an unknown class distribution from the target domain. This paper introduces a two-head convolutional neural network framework to solve all problems simultaneously. Our network consists of one common feature generator and two classifiers with different decision boundaries. By optimizing the divergence between the two classifiers' outputs, we can detect noisy source samples, find unknown classes in the target domain, and align the distribution of the source and target domains. In an extensive evaluation of different domain adaptation settings, the proposed method outperformed existing methods by a large margin in most settings." @default.
• W3139628984 created "2021-04-13" @default.
• W3139628984 creator A5038408644 @default.
• W3139628984 creator A5071338243 @default.
• W3139628984 creator A5077707500 @default.
• W3139628984 date "2021-04-01" @default.
• W3139628984 modified "2023-09-26" @default.
• W3139628984 title "Divergence Optimization for Noisy Universal Domain Adaptation" @default.
• W3139628984 cites W1565327149 @default.
• W3139628984 cites W1722318740 @default.
• W3139628984 cites W1731081199 @default.
• W3139628984 cites W1921293667 @default.
• W3139628984 cites W2048679005 @default.
• W3139628984 cites W2104094955 @default.
• W3139628984 cites W2133348086 @default.
• W3139628984 cites W2194775991 @default.
• W3139628984 cites W2250384498 @default.
• W3139628984 cites W2478454054 @default.
• W3139628984 cites W2511131004 @default.
• W3139628984 cites W2551835155 @default.
• W3139628984 cites W2593768305 @default.
• W3139628984 cites W2594718649 @default.
• W3139628984 cites W2627183927 @default.
• W3139628984 cites W2751528152 @default.
• W3139628984 cites W2766897166 @default.
• W3139628984 cites W2795155917 @default.
• W3139628984 cites W2798593490 @default.
• W3139628984 cites W2885722640 @default.
• W3139628984 cites W2904549000 @default.
• W3139628984 cites W2948069880 @default.
• W3139628984 cites W2948429981 @default.
• W3139628984 cites W2962687275 @default.
• W3139628984 cites W2962762541 @default.
• W3139628984 cites W2962835731 @default.
• W3139628984 cites W2962986791 @default.
• W3139628984 cites W2963081269 @default.
• W3139628984 cites W2963149653 @default.
• W3139628984 cites W2963275094 @default.
• W3139628984 cites W2963449430 @default.
• W3139628984 cites W2963735582 @default.
• W3139628984 cites W2963826681 @default.
• W3139628984 cites W2964139811 @default.
• W3139628984 cites W2964274690 @default.
• W3139628984 cites W2964292098 @default.
• W3139628984 cites W2964341837 @default.
• W3139628984 cites W2980096013 @default.
• W3139628984 cites W2981630749 @default.
• W3139628984 cites W2996364607 @default.
• W3139628984 cites W3034185248 @default.
• W3139628984 cites W3034363135 @default.
• W3139628984 cites W3137695714 @default.
• W3139628984 doi "https://doi.org/10.48550/arxiv.2104.00246" @default.
• W3139628984 hasPublicationYear "2021" @default.
• W3139628984 type Work @default.
• W3139628984 sameAs 3139628984 @default.
• W3139628984 citedByCount "0" @default.
• W3139628984 crossrefType "posted-content" @default.
• W3139628984 hasAuthorship W3139628984A5038408644 @default.
• W3139628984 hasAuthorship W3139628984A5071338243 @default.
• W3139628984 hasAuthorship W3139628984A5077707500 @default.
• W3139628984 hasBestOaLocation W31396289841 @default.
• W3139628984 hasConcept C105795698 @default.
• W3139628984 hasConcept C119857082 @default.
• W3139628984 hasConcept C120665830 @default.
• W3139628984 hasConcept C121332964 @default.
• W3139628984 hasConcept C124101348 @default.
• W3139628984 hasConcept C134306372 @default.
• W3139628984 hasConcept C138885662 @default.
• W3139628984 hasConcept C139807058 @default.
• W3139628984 hasConcept C150899416 @default.
• W3139628984 hasConcept C153180895 @default.
• W3139628984 hasConcept C154945302 @default.
• W3139628984 hasConcept C163258240 @default.
• W3139628984 hasConcept C207390915 @default.
• W3139628984 hasConcept C2776401178 @default.
• W3139628984 hasConcept C2776434776 @default.
• W3139628984 hasConcept C2780665216 @default.
• W3139628984 hasConcept C2780992000 @default.
• W3139628984 hasConcept C33923547 @default.
• W3139628984 hasConcept C36503486 @default.
• W3139628984 hasConcept C41008148 @default.
• W3139628984 hasConcept C41895202 @default.
• W3139628984 hasConcept C62520636 @default.
• W3139628984 hasConcept C774472 @default.
• W3139628984 hasConcept C81363708 @default.
• W3139628984 hasConcept C95623464 @default.
• W3139628984 hasConceptScore W3139628984C105795698 @default.
• W3139628984 hasConceptScore W3139628984C119857082 @default.
• W3139628984 hasConceptScore W3139628984C120665830 @default.
• W3139628984 hasConceptScore W3139628984C121332964 @default.
• W3139628984 hasConceptScore W3139628984C124101348 @default.
• W3139628984 hasConceptScore W3139628984C134306372 @default.
• W3139628984 hasConceptScore W3139628984C138885662 @default.
• W3139628984 hasConceptScore W3139628984C139807058 @default.
• W3139628984 hasConceptScore W3139628984C150899416 @default.
• W3139628984 hasConceptScore W3139628984C153180895 @default.
• W3139628984 hasConceptScore W3139628984C154945302 @default.
• W3139628984 hasConceptScore W3139628984C163258240 @default.
• W3139628984 hasConceptScore W3139628984C207390915 @default.
• W3139628984 hasConceptScore W3139628984C2776401178 @default.

• next