FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2004080111> ?p ?o ?g. }

• W2004080111 endingPage "3801" @default.
• W2004080111 startingPage "3789" @default.
• W2004080111 abstract "Distance metric learning (DML) is a critical factor for image analysis and pattern recognition. To learn a robust distance metric for a target task, we need abundant side information (i.e., the similarity/dissimilarity pairwise constraints over the labeled data), which is usually unavailable in practice due to the high labeling cost. This paper considers the transfer learning setting by exploiting the large quantity of side information from certain related, but different source tasks to help with target metric learning (with only a little side information). The state-of-the-art metric learning algorithms usually fail in this setting because the data distributions of the source task and target task are often quite different. We address this problem by assuming that the target distance metric lies in the space spanned by the eigenvectors of the source metrics (or other randomly generated bases). The target metric is represented as a combination of the base metrics, which are computed using the decomposed components of the source metrics (or simply a set of random bases); we call the proposed method, decomposition-based transfer DML (DTDML). In particular, DTDML learns a sparse combination of the base metrics to construct the target metric by forcing the target metric to be close to an integration of the source metrics. The main advantage of the proposed method compared with existing transfer metric learning approaches is that we directly learn the base metric coefficients instead of the target metric. To this end, far fewer variables need to be learned. We therefore obtain more reliable solutions given the limited side information and the optimization tends to be faster. Experiments on the popular handwritten image (digit, letter) classification and challenge natural image annotation tasks demonstrate the effectiveness of the proposed method." @default.
• W2004080111 created "2016-06-24" @default.
• W2004080111 creator A5033539867 @default.
• W2004080111 creator A5039158745 @default.
• W2004080111 creator A5065250332 @default.
• W2004080111 creator A5074103823 @default.
• W2004080111 date "2014-09-01" @default.
• W2004080111 modified "2023-10-13" @default.
• W2004080111 title "Decomposition-Based Transfer Distance Metric Learning for Image Classification" @default.
• W2004080111 cites W1984608801 @default.
• W2004080111 cites W1985583020 @default.
• W2004080111 cites W1988348003 @default.
• W2004080111 cites W2004465977 @default.
• W2004080111 cites W2007972815 @default.
• W2004080111 cites W2014987111 @default.
• W2004080111 cites W2017453188 @default.
• W2004080111 cites W2029213856 @default.
• W2004080111 cites W2053186076 @default.
• W2004080111 cites W2065180801 @default.
• W2004080111 cites W2072528130 @default.
• W2004080111 cites W2087923727 @default.
• W2004080111 cites W2099891036 @default.
• W2004080111 cites W2108013467 @default.
• W2004080111 cites W2122838776 @default.
• W2004080111 cites W2122922389 @default.
• W2004080111 cites W2137736727 @default.
• W2004080111 cites W2141581971 @default.
• W2004080111 cites W2143104527 @default.
• W2004080111 cites W2147690544 @default.
• W2004080111 cites W2151103935 @default.
• W2004080111 cites W2158108973 @default.
• W2004080111 cites W2159748429 @default.
• W2004080111 cites W2165698076 @default.
• W2004080111 cites W2167732364 @default.
• W2004080111 cites W2169495281 @default.
• W2004080111 cites W2536305071 @default.
• W2004080111 cites W2989661724 @default.
• W2004080111 doi "https://doi.org/10.1109/tip.2014.2332398" @default.
• W2004080111 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/24968169" @default.
• W2004080111 hasPublicationYear "2014" @default.
• W2004080111 type Work @default.
• W2004080111 sameAs 2004080111 @default.
• W2004080111 citedByCount "96" @default.
• W2004080111 countsByYear W20040801112014 @default.
• W2004080111 countsByYear W20040801112015 @default.
• W2004080111 countsByYear W20040801112016 @default.
• W2004080111 countsByYear W20040801112017 @default.
• W2004080111 countsByYear W20040801112018 @default.
• W2004080111 countsByYear W20040801112019 @default.
• W2004080111 countsByYear W20040801112020 @default.
• W2004080111 countsByYear W20040801112021 @default.
• W2004080111 countsByYear W20040801112022 @default.
• W2004080111 countsByYear W20040801112023 @default.
• W2004080111 crossrefType "journal-article" @default.
• W2004080111 hasAuthorship W2004080111A5033539867 @default.
• W2004080111 hasAuthorship W2004080111A5039158745 @default.
• W2004080111 hasAuthorship W2004080111A5065250332 @default.
• W2004080111 hasAuthorship W2004080111A5074103823 @default.
• W2004080111 hasBestOaLocation W20040801112 @default.
• W2004080111 hasConcept C103278499 @default.
• W2004080111 hasConcept C115961682 @default.
• W2004080111 hasConcept C119857082 @default.
• W2004080111 hasConcept C134306372 @default.
• W2004080111 hasConcept C150899416 @default.
• W2004080111 hasConcept C153180895 @default.
• W2004080111 hasConcept C154945302 @default.
• W2004080111 hasConcept C162324750 @default.
• W2004080111 hasConcept C176217482 @default.
• W2004080111 hasConcept C177264268 @default.
• W2004080111 hasConcept C184898388 @default.
• W2004080111 hasConcept C191226916 @default.
• W2004080111 hasConcept C196613150 @default.
• W2004080111 hasConcept C198043062 @default.
• W2004080111 hasConcept C199360897 @default.
• W2004080111 hasConcept C21547014 @default.
• W2004080111 hasConcept C22820288 @default.
• W2004080111 hasConcept C33923547 @default.
• W2004080111 hasConcept C41008148 @default.
• W2004080111 hasConcept C68859911 @default.
• W2004080111 hasConcept C7757238 @default.
• W2004080111 hasConceptScore W2004080111C103278499 @default.
• W2004080111 hasConceptScore W2004080111C115961682 @default.
• W2004080111 hasConceptScore W2004080111C119857082 @default.
• W2004080111 hasConceptScore W2004080111C134306372 @default.
• W2004080111 hasConceptScore W2004080111C150899416 @default.
• W2004080111 hasConceptScore W2004080111C153180895 @default.
• W2004080111 hasConceptScore W2004080111C154945302 @default.
• W2004080111 hasConceptScore W2004080111C162324750 @default.
• W2004080111 hasConceptScore W2004080111C176217482 @default.
• W2004080111 hasConceptScore W2004080111C177264268 @default.
• W2004080111 hasConceptScore W2004080111C184898388 @default.
• W2004080111 hasConceptScore W2004080111C191226916 @default.
• W2004080111 hasConceptScore W2004080111C196613150 @default.
• W2004080111 hasConceptScore W2004080111C198043062 @default.
• W2004080111 hasConceptScore W2004080111C199360897 @default.
• W2004080111 hasConceptScore W2004080111C21547014 @default.
• W2004080111 hasConceptScore W2004080111C22820288 @default.
• W2004080111 hasConceptScore W2004080111C33923547 @default.

• next