FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2022658925> ?p ?o ?g. }

• W2022658925 abstract "We consider the intersection of two research fields: transfer learning and statistics on manifolds. In particu- lar, we consider, for manifold-valued data, transfer learn- ing of tangent-space models such as Gaussians distribu- tions, PCA, regression, or classifiers. Though one would hope to simply use ordinary Rn-transfer learning ideas, the manifold structure prevents it. We overcome this by basing our method on inner-product-preserving parallel transport, a well-known tool widely used in other problems of statis- tics on manifolds in computer vision. At first, this straight- forward idea seems to suffer from an obvious shortcom- ing: Transporting large datasets is prohibitively expensive, hindering scalability. Fortunately, with our approach, we never transport data. Rather, we show how the statistical models themselves can be transported, and prove that for the tangent-space models above, the transport commutes with learning. Consequently, our compact framework, ap- plicable to a large class of manifolds, is not restricted by the size of either the training or test sets. We demonstrate the approach by transferring PCA and logistic-regression models of real-world data involving 3D shapes and image descriptors." @default.
• W2022658925 created "2016-06-24" @default.
• W2022658925 creator A5065396778 @default.
• W2022658925 creator A5072186051 @default.
• W2022658925 creator A5082095784 @default.
• W2022658925 date "2014-06-01" @default.
• W2022658925 modified "2023-09-25" @default.
• W2022658925 title "Model Transport: Towards Scalable Transfer Learning on Manifolds" @default.
• W2022658925 cites W1503893179 @default.
• W2022658925 cites W1540708136 @default.
• W2022658925 cites W1550411400 @default.
• W2022658925 cites W1564897360 @default.
• W2022658925 cites W158678268 @default.
• W2022658925 cites W1745126362 @default.
• W2022658925 cites W194200989 @default.
• W2022658925 cites W1983496390 @default.
• W2022658925 cites W1990512452 @default.
• W2022658925 cites W2011194978 @default.
• W2022658925 cites W2015440243 @default.
• W2022658925 cites W2024897941 @default.
• W2022658925 cites W2041339162 @default.
• W2022658925 cites W2042830903 @default.
• W2022658925 cites W2045512849 @default.
• W2022658925 cites W2048192550 @default.
• W2022658925 cites W2068376131 @default.
• W2022658925 cites W2079842261 @default.
• W2022658925 cites W2081834074 @default.
• W2022658925 cites W2091804476 @default.
• W2022658925 cites W2105866209 @default.
• W2022658925 cites W2109247271 @default.
• W2022658925 cites W2120354757 @default.
• W2022658925 cites W2120708938 @default.
• W2022658925 cites W2123678129 @default.
• W2022658925 cites W2125949583 @default.
• W2022658925 cites W2130899515 @default.
• W2022658925 cites W2134080476 @default.
• W2022658925 cites W2145072179 @default.
• W2022658925 cites W2146932984 @default.
• W2022658925 cites W2149466042 @default.
• W2022658925 cites W2158911079 @default.
• W2022658925 cites W2162744734 @default.
• W2022658925 cites W2169678505 @default.
• W2022658925 cites W2170167891 @default.
• W2022658925 cites W2171710593 @default.
• W2022658925 cites W2184041750 @default.
• W2022658925 cites W22024230 @default.
• W2022658925 cites W2212721536 @default.
• W2022658925 cites W3038420293 @default.
• W2022658925 cites W3217246742 @default.
• W2022658925 cites W645520567 @default.
• W2022658925 cites W848340010 @default.
• W2022658925 cites W2585165747 @default.
• W2022658925 doi "https://doi.org/10.1109/cvpr.2014.179" @default.
• W2022658925 hasPublicationYear "2014" @default.
• W2022658925 type Work @default.
• W2022658925 sameAs 2022658925 @default.
• W2022658925 citedByCount "22" @default.
• W2022658925 countsByYear W20226589252014 @default.
• W2022658925 countsByYear W20226589252015 @default.
• W2022658925 countsByYear W20226589252016 @default.
• W2022658925 countsByYear W20226589252017 @default.
• W2022658925 countsByYear W20226589252018 @default.
• W2022658925 countsByYear W20226589252019 @default.
• W2022658925 countsByYear W20226589252020 @default.
• W2022658925 countsByYear W20226589252021 @default.
• W2022658925 crossrefType "proceedings-article" @default.
• W2022658925 hasAuthorship W2022658925A5065396778 @default.
• W2022658925 hasAuthorship W2022658925A5072186051 @default.
• W2022658925 hasAuthorship W2022658925A5082095784 @default.
• W2022658925 hasBestOaLocation W20226589252 @default.
• W2022658925 hasConcept C111919701 @default.
• W2022658925 hasConcept C11413529 @default.
• W2022658925 hasConcept C119857082 @default.
• W2022658925 hasConcept C127413603 @default.
• W2022658925 hasConcept C138187205 @default.
• W2022658925 hasConcept C150899416 @default.
• W2022658925 hasConcept C151876577 @default.
• W2022658925 hasConcept C154945302 @default.
• W2022658925 hasConcept C157157409 @default.
• W2022658925 hasConcept C205649164 @default.
• W2022658925 hasConcept C2524010 @default.
• W2022658925 hasConcept C2777212361 @default.
• W2022658925 hasConcept C2778572836 @default.
• W2022658925 hasConcept C33923547 @default.
• W2022658925 hasConcept C41008148 @default.
• W2022658925 hasConcept C48044578 @default.
• W2022658925 hasConcept C529865628 @default.
• W2022658925 hasConcept C58640448 @default.
• W2022658925 hasConcept C64543145 @default.
• W2022658925 hasConcept C70518039 @default.
• W2022658925 hasConcept C77088390 @default.
• W2022658925 hasConcept C774472 @default.
• W2022658925 hasConcept C78519656 @default.
• W2022658925 hasConceptScore W2022658925C111919701 @default.
• W2022658925 hasConceptScore W2022658925C11413529 @default.
• W2022658925 hasConceptScore W2022658925C119857082 @default.
• W2022658925 hasConceptScore W2022658925C127413603 @default.
• W2022658925 hasConceptScore W2022658925C138187205 @default.
• W2022658925 hasConceptScore W2022658925C150899416 @default.
• W2022658925 hasConceptScore W2022658925C151876577 @default.

• next