Matches in SemOpenAlex for { <https://semopenalex.org/work/W2743293577> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2743293577 endingPage "119" @default.
- W2743293577 startingPage "95" @default.
- W2743293577 abstract "The lack of labeled data presents a common challenge in many computer vision and machine learning tasks. Semi-supervised learning and transfer learning methods have been developed to tackle this challenge by utilizing auxiliary samples from the same domain or from a different domain, respectively. Self-taught learning, which is a special type of transfer learning, has fewer restrictions on the choice of auxiliary data. It has shown promising performance in visual learning. However, existing self-taught learning methods usually ignore the structure information in data. In this chapter, we focus on building a self-taught coding framework, which can effectively utilize the rich low-level pattern information abstracted from the auxiliary domain, in order to characterize the high-level structural information in the target domain. By leveraging a high quality dictionary learned across auxiliary and target domains, the proposed approach learns expressive codings for the samples in the target domain. Since many types of visual data have been proven to contain subspace structures, a low-rank constraint is introduced into the coding objective to better characterize the structure of the given target set. The proposed representation learning framework is called Self-taught Low-rank coding (S-Low), which can be formulated as a non-convex rank-minimization and dictionary learning problem. We devise an efficient majorization-minimization augmented Lagrange multiplier (MM-ALM) algorithm to solve it. Based on the proposed S-Low coding mechanism, both unsupervised and supervised visual learning algorithms are derived. Extensive experiments on five benchmark datasets demonstrate the effectiveness of our approach." @default.
- W2743293577 created "2017-08-17" @default.
- W2743293577 creator A5005819096 @default.
- W2743293577 creator A5026512168 @default.
- W2743293577 date "2017-01-01" @default.
- W2743293577 modified "2023-09-26" @default.
- W2743293577 title "Robust Dictionary Learning" @default.
- W2743293577 cites W1890623278 @default.
- W2743293577 cites W1910772337 @default.
- W2743293577 cites W1965125844 @default.
- W2743293577 cites W1982344527 @default.
- W2743293577 cites W1982696459 @default.
- W2743293577 cites W1997201895 @default.
- W2743293577 cites W2007588387 @default.
- W2743293577 cites W2040329636 @default.
- W2743293577 cites W2052293776 @default.
- W2743293577 cites W2066941820 @default.
- W2743293577 cites W2083177649 @default.
- W2743293577 cites W2087107531 @default.
- W2743293577 cites W2088164725 @default.
- W2743293577 cites W2113606819 @default.
- W2743293577 cites W2115575686 @default.
- W2743293577 cites W2121947440 @default.
- W2743293577 cites W2122922389 @default.
- W2743293577 cites W2129517580 @default.
- W2743293577 cites W2129812935 @default.
- W2743293577 cites W2130623086 @default.
- W2743293577 cites W2145152441 @default.
- W2743293577 cites W2145962650 @default.
- W2743293577 cites W2157785665 @default.
- W2743293577 cites W2158911526 @default.
- W2743293577 cites W2162915993 @default.
- W2743293577 cites W2163922914 @default.
- W2743293577 cites W2165698076 @default.
- W2743293577 cites W2273827415 @default.
- W2743293577 cites W2279365017 @default.
- W2743293577 cites W2294193936 @default.
- W2743293577 cites W2344457357 @default.
- W2743293577 cites W2552987523 @default.
- W2743293577 cites W4230674625 @default.
- W2743293577 cites W580709845 @default.
- W2743293577 cites W96659543 @default.
- W2743293577 doi "https://doi.org/10.1007/978-3-319-60176-2_6" @default.
- W2743293577 hasPublicationYear "2017" @default.
- W2743293577 type Work @default.
- W2743293577 sameAs 2743293577 @default.
- W2743293577 citedByCount "0" @default.
- W2743293577 crossrefType "book-chapter" @default.
- W2743293577 hasAuthorship W2743293577A5005819096 @default.
- W2743293577 hasAuthorship W2743293577A5026512168 @default.
- W2743293577 hasConcept C105795698 @default.
- W2743293577 hasConcept C119857082 @default.
- W2743293577 hasConcept C150899416 @default.
- W2743293577 hasConcept C154945302 @default.
- W2743293577 hasConcept C179518139 @default.
- W2743293577 hasConcept C189430467 @default.
- W2743293577 hasConcept C32834561 @default.
- W2743293577 hasConcept C33923547 @default.
- W2743293577 hasConcept C41008148 @default.
- W2743293577 hasConcept C58973888 @default.
- W2743293577 hasConcept C59404180 @default.
- W2743293577 hasConcept C77637269 @default.
- W2743293577 hasConcept C86037889 @default.
- W2743293577 hasConceptScore W2743293577C105795698 @default.
- W2743293577 hasConceptScore W2743293577C119857082 @default.
- W2743293577 hasConceptScore W2743293577C150899416 @default.
- W2743293577 hasConceptScore W2743293577C154945302 @default.
- W2743293577 hasConceptScore W2743293577C179518139 @default.
- W2743293577 hasConceptScore W2743293577C189430467 @default.
- W2743293577 hasConceptScore W2743293577C32834561 @default.
- W2743293577 hasConceptScore W2743293577C33923547 @default.
- W2743293577 hasConceptScore W2743293577C41008148 @default.
- W2743293577 hasConceptScore W2743293577C58973888 @default.
- W2743293577 hasConceptScore W2743293577C59404180 @default.
- W2743293577 hasConceptScore W2743293577C77637269 @default.
- W2743293577 hasConceptScore W2743293577C86037889 @default.
- W2743293577 hasLocation W27432935771 @default.
- W2743293577 hasOpenAccess W2743293577 @default.
- W2743293577 hasPrimaryLocation W27432935771 @default.
- W2743293577 hasRelatedWork W2946016983 @default.
- W2743293577 hasRelatedWork W2954428433 @default.
- W2743293577 hasRelatedWork W2960456850 @default.
- W2743293577 hasRelatedWork W3021430260 @default.
- W2743293577 hasRelatedWork W3025582806 @default.
- W2743293577 hasRelatedWork W3169943726 @default.
- W2743293577 hasRelatedWork W4281645081 @default.
- W2743293577 hasRelatedWork W4308262314 @default.
- W2743293577 hasRelatedWork W4312200629 @default.
- W2743293577 hasRelatedWork W4382286161 @default.
- W2743293577 isParatext "false" @default.
- W2743293577 isRetracted "false" @default.
- W2743293577 magId "2743293577" @default.
- W2743293577 workType "book-chapter" @default.