Matches in SemOpenAlex for { <https://semopenalex.org/work/W2095979710> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2095979710 abstract "The k-nearest neighbour (kNN) rule is a simple and effective method for multi-way classification that is much used in Computer Vision. However, its performance depends heavily on the distance metric being employed. The recently proposed large margin nearest neighbour (LMNN) classifier [21] learns a distance metric for kNN classification and thereby improves its accuracy. Learning involves optimizing a convex problem using semidefinite programming (SDP). We extend the LMNN framework to incorporate knowledge about invariance of the data. The main contributions of our work are three fold: (i) Invariances to multivariate polynomial transformations are incorporated without explicitly adding more training data during learning - these can approximate common transformations such as rotations and affinities; (ii) the incorporation of different regularizes on the parameters being learnt; and (Hi) for all these variations, we show that the distance metric can still be obtained by solving a convex SDP problem. We call the resulting formulation invariant LMNN (lLMNN) classifier. We test our approach to learn a metric for matching (i) feature vectors from the standard Iris dataset; and (ii) faces obtained from TV video (an episode of 'Buffy the Vampire Slayer'). We compare our method with the state of the art classifiers and demonstrate improvements." @default.
- W2095979710 created "2016-06-24" @default.
- W2095979710 creator A5001534492 @default.
- W2095979710 creator A5018728658 @default.
- W2095979710 creator A5057678172 @default.
- W2095979710 date "2007-01-01" @default.
- W2095979710 modified "2023-09-28" @default.
- W2095979710 title "An Invariant Large Margin Nearest Neighbour Classifier" @default.
- W2095979710 cites W1733921475 @default.
- W2095979710 cites W1967344706 @default.
- W2095979710 cites W2012266246 @default.
- W2095979710 cites W2033511209 @default.
- W2095979710 cites W2101974476 @default.
- W2095979710 cites W2104752854 @default.
- W2095979710 cites W2122111042 @default.
- W2095979710 cites W2122246689 @default.
- W2095979710 cites W2130556178 @default.
- W2095979710 cites W2137291015 @default.
- W2095979710 cites W2143075842 @default.
- W2095979710 cites W2147609908 @default.
- W2095979710 cites W2151103935 @default.
- W2095979710 cites W2152010828 @default.
- W2095979710 cites W2152926413 @default.
- W2095979710 cites W2159543502 @default.
- W2095979710 cites W2165828254 @default.
- W2095979710 cites W2168996682 @default.
- W2095979710 cites W2548960858 @default.
- W2095979710 cites W1806104592 @default.
- W2095979710 doi "https://doi.org/10.1109/iccv.2007.4409041" @default.
- W2095979710 hasPublicationYear "2007" @default.
- W2095979710 type Work @default.
- W2095979710 sameAs 2095979710 @default.
- W2095979710 citedByCount "37" @default.
- W2095979710 countsByYear W20959797102012 @default.
- W2095979710 countsByYear W20959797102013 @default.
- W2095979710 countsByYear W20959797102014 @default.
- W2095979710 countsByYear W20959797102015 @default.
- W2095979710 countsByYear W20959797102016 @default.
- W2095979710 countsByYear W20959797102018 @default.
- W2095979710 countsByYear W20959797102020 @default.
- W2095979710 countsByYear W20959797102021 @default.
- W2095979710 countsByYear W20959797102022 @default.
- W2095979710 crossrefType "proceedings-article" @default.
- W2095979710 hasAuthorship W2095979710A5001534492 @default.
- W2095979710 hasAuthorship W2095979710A5018728658 @default.
- W2095979710 hasAuthorship W2095979710A5057678172 @default.
- W2095979710 hasConcept C101901036 @default.
- W2095979710 hasConcept C113238511 @default.
- W2095979710 hasConcept C116738811 @default.
- W2095979710 hasConcept C126255220 @default.
- W2095979710 hasConcept C153180895 @default.
- W2095979710 hasConcept C154945302 @default.
- W2095979710 hasConcept C190470478 @default.
- W2095979710 hasConcept C33923547 @default.
- W2095979710 hasConcept C37914503 @default.
- W2095979710 hasConcept C41008148 @default.
- W2095979710 hasConcept C50644808 @default.
- W2095979710 hasConcept C60908668 @default.
- W2095979710 hasConcept C94475309 @default.
- W2095979710 hasConcept C95623464 @default.
- W2095979710 hasConceptScore W2095979710C101901036 @default.
- W2095979710 hasConceptScore W2095979710C113238511 @default.
- W2095979710 hasConceptScore W2095979710C116738811 @default.
- W2095979710 hasConceptScore W2095979710C126255220 @default.
- W2095979710 hasConceptScore W2095979710C153180895 @default.
- W2095979710 hasConceptScore W2095979710C154945302 @default.
- W2095979710 hasConceptScore W2095979710C190470478 @default.
- W2095979710 hasConceptScore W2095979710C33923547 @default.
- W2095979710 hasConceptScore W2095979710C37914503 @default.
- W2095979710 hasConceptScore W2095979710C41008148 @default.
- W2095979710 hasConceptScore W2095979710C50644808 @default.
- W2095979710 hasConceptScore W2095979710C60908668 @default.
- W2095979710 hasConceptScore W2095979710C94475309 @default.
- W2095979710 hasConceptScore W2095979710C95623464 @default.
- W2095979710 hasLocation W20959797101 @default.
- W2095979710 hasOpenAccess W2095979710 @default.
- W2095979710 hasPrimaryLocation W20959797101 @default.
- W2095979710 hasRelatedWork W1985839407 @default.
- W2095979710 hasRelatedWork W2014633245 @default.
- W2095979710 hasRelatedWork W2015098463 @default.
- W2095979710 hasRelatedWork W2125644499 @default.
- W2095979710 hasRelatedWork W2130556178 @default.
- W2095979710 hasRelatedWork W2535288021 @default.
- W2095979710 hasRelatedWork W2604397568 @default.
- W2095979710 hasRelatedWork W2759927763 @default.
- W2095979710 hasRelatedWork W2765876051 @default.
- W2095979710 hasRelatedWork W2964189006 @default.
- W2095979710 isParatext "false" @default.
- W2095979710 isRetracted "false" @default.
- W2095979710 magId "2095979710" @default.
- W2095979710 workType "article" @default.