FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034765384> ?p ?o ?g. }

• W3034765384 abstract "A complex combination of simultaneous supervised-unsupervised learning is believed to be the key to humans performing tasks seamlessly across multiple domains or tasks. This phenomenon of cross-domain learning has been very well studied in domain adaptation literature. Recent domain adaptation works rely on an indirect way of first aligning the source and target domain distributions and then train a classifier on the labeled source domain to classify the target domain. However, this approach has the main drawback that obtaining a near-perfect alignment of the domains in itself might be difficult/impossible (e.g., language domains). To address this, we follow Vapnik's imperative of statistical learning that states any desired problem should be solved in the most direct way rather than solving a more general intermediate task and propose a direct approach to domain adaptation that does not require domain alignment. We propose a model referred Contradistinguisher that learns contrastive features and whose objective is to jointly learn to contradistinguish the unlabeled target domain in an unsupervised way and classify in a supervised way on the source domain. We achieve the state-of-the-art on Office-31 and VisDA-2017 datasets in both single-source and multi-source settings. We also demonstrate that the contradistinguish loss improves the model performance by increasing the shape bias." @default.
• W3034765384 created "2020-06-19" @default.
• W3034765384 creator A5010292297 @default.
• W3034765384 creator A5036246275 @default.
• W3034765384 date "2020-05-25" @default.
• W3034765384 modified "2023-09-27" @default.
• W3034765384 title "Contradistinguisher: A Vapnik's Imperative to Unsupervised Domain Adaptation" @default.
• W3034765384 cites W1722318740 @default.
• W3034765384 cites W1836465849 @default.
• W3034765384 cites W1861492603 @default.
• W3034765384 cites W1959608418 @default.
• W3034765384 cites W1970571032 @default.
• W3034765384 cites W2006662684 @default.
• W3034765384 cites W2023443487 @default.
• W3034765384 cites W2049633694 @default.
• W3034765384 cites W2099471712 @default.
• W3034765384 cites W2101234009 @default.
• W3034765384 cites W2110176078 @default.
• W3034765384 cites W2112796928 @default.
• W3034765384 cites W2119044918 @default.
• W3034765384 cites W2128053425 @default.
• W3034765384 cites W2145494108 @default.
• W3034765384 cites W2147800946 @default.
• W3034765384 cites W2149298154 @default.
• W3034765384 cites W2156909104 @default.
• W3034765384 cites W2159291411 @default.
• W3034765384 cites W2187089797 @default.
• W3034765384 cites W2194775991 @default.
• W3034765384 cites W2212660284 @default.
• W3034765384 cites W2279034837 @default.
• W3034765384 cites W2312004824 @default.
• W3034765384 cites W2335728318 @default.
• W3034765384 cites W2478454054 @default.
• W3034765384 cites W2511131004 @default.
• W3034765384 cites W2592463526 @default.
• W3034765384 cites W2592691248 @default.
• W3034765384 cites W2593768305 @default.
• W3034765384 cites W2594718649 @default.
• W3034765384 cites W2605488490 @default.
• W3034765384 cites W2617027347 @default.
• W3034765384 cites W2744915377 @default.
• W3034765384 cites W2766897166 @default.
• W3034765384 cites W2773004715 @default.
• W3034765384 cites W2795155917 @default.
• W3034765384 cites W2800222246 @default.
• W3034765384 cites W2803297029 @default.
• W3034765384 cites W2899771611 @default.
• W3034765384 cites W2946812986 @default.
• W3034765384 cites W2948959975 @default.
• W3034765384 cites W2962687275 @default.
• W3034765384 cites W2962750142 @default.
• W3034765384 cites W2962768284 @default.
• W3034765384 cites W2962808524 @default.
• W3034765384 cites W2962851944 @default.
• W3034765384 cites W2962892300 @default.
• W3034765384 cites W2962940674 @default.
• W3034765384 cites W2962970380 @default.
• W3034765384 cites W2963217615 @default.
• W3034765384 cites W2963240485 @default.
• W3034765384 cites W2963449430 @default.
• W3034765384 cites W2963488527 @default.
• W3034765384 cites W2963506806 @default.
• W3034765384 cites W2963532621 @default.
• W3034765384 cites W2963571818 @default.
• W3034765384 cites W2963784072 @default.
• W3034765384 cites W2963826681 @default.
• W3034765384 cites W2963864946 @default.
• W3034765384 cites W2963870446 @default.
• W3034765384 cites W2964117661 @default.
• W3034765384 cites W2964278684 @default.
• W3034765384 cites W2964314879 @default.
• W3034765384 cites W2964352424 @default.
• W3034765384 cites W2967691516 @default.
• W3034765384 cites W2970987681 @default.
• W3034765384 cites W2978573218 @default.
• W3034765384 cites W2981720610 @default.
• W3034765384 cites W3018638193 @default.
• W3034765384 cites W3026414903 @default.
• W3034765384 cites W2530816535 @default.
• W3034765384 hasPublicationYear "2020" @default.
• W3034765384 type Work @default.
• W3034765384 sameAs 3034765384 @default.
• W3034765384 citedByCount "0" @default.
• W3034765384 crossrefType "posted-content" @default.
• W3034765384 hasAuthorship W3034765384A5010292297 @default.
• W3034765384 hasAuthorship W3034765384A5036246275 @default.
• W3034765384 hasConcept C119857082 @default.
• W3034765384 hasConcept C120665830 @default.
• W3034765384 hasConcept C121332964 @default.
• W3034765384 hasConcept C134306372 @default.
• W3034765384 hasConcept C139807058 @default.
• W3034765384 hasConcept C153180895 @default.
• W3034765384 hasConcept C154945302 @default.
• W3034765384 hasConcept C162324750 @default.
• W3034765384 hasConcept C187736073 @default.
• W3034765384 hasConcept C2776145971 @default.
• W3034765384 hasConcept C2776434776 @default.
• W3034765384 hasConcept C2780451532 @default.
• W3034765384 hasConcept C33923547 @default.
• W3034765384 hasConcept C36503486 @default.

• next