Matches in SemOpenAlex for { <https://semopenalex.org/work/W1969600701> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W1969600701 abstract "Learning low-dimensional feature representations is a crucial task in machine learning and computer vision. Recently the impressive breakthrough in general object recognition made by large scale convolutional networks shows that convolutional networks are able to extract discriminative hierarchical features in large scale object classification task. However, for vision tasks other than end-to-end classification, such as K Nearest Neighbor classification, the learned intermediate features are not necessary optimal for the specific problem. In this paper, we aim to exploit the power of deep convolutional networks and optimize the output feature layer with respect to the task of K Nearest Neighbor (kNN) classification. By directly optimizing the kNN classification error on training data, we in fact learn convolutional nonlinear features in a data-driven and task-driven way. Experimental results on standard image classification benchmarks show that the proposed method is able to learn better feature representations than other general end-to-end classification methods on kNN classification task." @default.
- W1969600701 created "2016-06-24" @default.
- W1969600701 creator A5011772578 @default.
- W1969600701 creator A5028693655 @default.
- W1969600701 creator A5036087177 @default.
- W1969600701 creator A5057947122 @default.
- W1969600701 date "2014-08-01" @default.
- W1969600701 modified "2023-10-16" @default.
- W1969600701 title "Learning Convolutional Nonlinear Features for K Nearest Neighbor Image Classification" @default.
- W1969600701 cites W2022508996 @default.
- W1969600701 cites W2112796928 @default.
- W1969600701 cites W2136922672 @default.
- W1969600701 cites W2138621090 @default.
- W1969600701 cites W2145607950 @default.
- W1969600701 cites W2151103935 @default.
- W1969600701 cites W2169495281 @default.
- W1969600701 cites W4231109964 @default.
- W1969600701 doi "https://doi.org/10.1109/icpr.2014.746" @default.
- W1969600701 hasPublicationYear "2014" @default.
- W1969600701 type Work @default.
- W1969600701 sameAs 1969600701 @default.
- W1969600701 citedByCount "10" @default.
- W1969600701 countsByYear W19696007012015 @default.
- W1969600701 countsByYear W19696007012018 @default.
- W1969600701 countsByYear W19696007012019 @default.
- W1969600701 countsByYear W19696007012020 @default.
- W1969600701 countsByYear W19696007012021 @default.
- W1969600701 countsByYear W19696007012022 @default.
- W1969600701 crossrefType "proceedings-article" @default.
- W1969600701 hasAuthorship W1969600701A5011772578 @default.
- W1969600701 hasAuthorship W1969600701A5028693655 @default.
- W1969600701 hasAuthorship W1969600701A5036087177 @default.
- W1969600701 hasAuthorship W1969600701A5057947122 @default.
- W1969600701 hasBestOaLocation W19696007012 @default.
- W1969600701 hasConcept C108583219 @default.
- W1969600701 hasConcept C113238511 @default.
- W1969600701 hasConcept C115961682 @default.
- W1969600701 hasConcept C119857082 @default.
- W1969600701 hasConcept C138885662 @default.
- W1969600701 hasConcept C153180895 @default.
- W1969600701 hasConcept C154945302 @default.
- W1969600701 hasConcept C162324750 @default.
- W1969600701 hasConcept C187736073 @default.
- W1969600701 hasConcept C2776401178 @default.
- W1969600701 hasConcept C2780451532 @default.
- W1969600701 hasConcept C41008148 @default.
- W1969600701 hasConcept C41895202 @default.
- W1969600701 hasConcept C52622490 @default.
- W1969600701 hasConcept C75294576 @default.
- W1969600701 hasConcept C81363708 @default.
- W1969600701 hasConcept C97931131 @default.
- W1969600701 hasConceptScore W1969600701C108583219 @default.
- W1969600701 hasConceptScore W1969600701C113238511 @default.
- W1969600701 hasConceptScore W1969600701C115961682 @default.
- W1969600701 hasConceptScore W1969600701C119857082 @default.
- W1969600701 hasConceptScore W1969600701C138885662 @default.
- W1969600701 hasConceptScore W1969600701C153180895 @default.
- W1969600701 hasConceptScore W1969600701C154945302 @default.
- W1969600701 hasConceptScore W1969600701C162324750 @default.
- W1969600701 hasConceptScore W1969600701C187736073 @default.
- W1969600701 hasConceptScore W1969600701C2776401178 @default.
- W1969600701 hasConceptScore W1969600701C2780451532 @default.
- W1969600701 hasConceptScore W1969600701C41008148 @default.
- W1969600701 hasConceptScore W1969600701C41895202 @default.
- W1969600701 hasConceptScore W1969600701C52622490 @default.
- W1969600701 hasConceptScore W1969600701C75294576 @default.
- W1969600701 hasConceptScore W1969600701C81363708 @default.
- W1969600701 hasConceptScore W1969600701C97931131 @default.
- W1969600701 hasLocation W19696007011 @default.
- W1969600701 hasLocation W19696007012 @default.
- W1969600701 hasOpenAccess W1969600701 @default.
- W1969600701 hasPrimaryLocation W19696007011 @default.
- W1969600701 hasRelatedWork W2406522397 @default.
- W1969600701 hasRelatedWork W2518599539 @default.
- W1969600701 hasRelatedWork W2546942002 @default.
- W1969600701 hasRelatedWork W2732542196 @default.
- W1969600701 hasRelatedWork W2760085659 @default.
- W1969600701 hasRelatedWork W2914959431 @default.
- W1969600701 hasRelatedWork W2940977206 @default.
- W1969600701 hasRelatedWork W3011074480 @default.
- W1969600701 hasRelatedWork W3156786002 @default.
- W1969600701 hasRelatedWork W4311257506 @default.
- W1969600701 isParatext "false" @default.
- W1969600701 isRetracted "false" @default.
- W1969600701 magId "1969600701" @default.
- W1969600701 workType "article" @default.