Matches in SemOpenAlex for { <https://semopenalex.org/work/W2808657737> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2808657737 abstract "Prototype selection is a promising technique for removing redundancy and irrelevance from large-scale data. Here, we consider it as a task assignment problem, which refers to assigning each element of a source set to one representative, i.e., prototype. However, due to the outliers and uncertain distribution on source, the selected prototypes are generally less representative and interesting. To alleviate this issue, we develop in this paper a Self-supervised Deep Low-rank Assignment model (SDLA). By dynamically integrating a low-rank assignment model with deep representation learning, our model effectively ensures the goodness-of-exemplar and goodness-of-discrimination of selected prototypes. Specifically, on the basis of a denoising autoencoder, dissimilarity metrics on source are continuously self-refined in embedding space with weak supervision from selected prototypes, thus preserving categorical similarity. Conversely, working on this metric space, similar samples tend to select the same prototypes by designing a low-rank assignment model. Experimental results on applications like text clustering and image classification (using prototypes) demonstrate our method is considerably superior to the state-of-the-art methods in prototype selection." @default.
- W2808657737 created "2018-06-21" @default.
- W2808657737 creator A5017102094 @default.
- W2808657737 creator A5028127027 @default.
- W2808657737 creator A5068473312 @default.
- W2808657737 creator A5078189730 @default.
- W2808657737 date "2018-07-01" @default.
- W2808657737 modified "2023-09-26" @default.
- W2808657737 title "Self-Supervised Deep Low-Rank Assignment Model for Prototype Selection" @default.
- W2808657737 cites W1686810756 @default.
- W2808657737 cites W1966872876 @default.
- W2808657737 cites W2012931101 @default.
- W2808657737 cites W2051549110 @default.
- W2808657737 cites W2100659887 @default.
- W2808657737 cites W2109209963 @default.
- W2808657737 cites W2151537585 @default.
- W2808657737 cites W2160941318 @default.
- W2808657737 cites W2162915993 @default.
- W2808657737 cites W2163922914 @default.
- W2808657737 cites W2167930540 @default.
- W2808657737 cites W2169658215 @default.
- W2808657737 cites W2262946425 @default.
- W2808657737 cites W2471931546 @default.
- W2808657737 doi "https://doi.org/10.24963/ijcai.2018/436" @default.
- W2808657737 hasPublicationYear "2018" @default.
- W2808657737 type Work @default.
- W2808657737 sameAs 2808657737 @default.
- W2808657737 citedByCount "8" @default.
- W2808657737 countsByYear W28086577372018 @default.
- W2808657737 countsByYear W28086577372019 @default.
- W2808657737 countsByYear W28086577372020 @default.
- W2808657737 countsByYear W28086577372021 @default.
- W2808657737 countsByYear W28086577372022 @default.
- W2808657737 crossrefType "proceedings-article" @default.
- W2808657737 hasAuthorship W2808657737A5017102094 @default.
- W2808657737 hasAuthorship W2808657737A5028127027 @default.
- W2808657737 hasAuthorship W2808657737A5068473312 @default.
- W2808657737 hasAuthorship W2808657737A5078189730 @default.
- W2808657737 hasBestOaLocation W28086577371 @default.
- W2808657737 hasConcept C103278499 @default.
- W2808657737 hasConcept C111919701 @default.
- W2808657737 hasConcept C114614502 @default.
- W2808657737 hasConcept C115961682 @default.
- W2808657737 hasConcept C119857082 @default.
- W2808657737 hasConcept C124101348 @default.
- W2808657737 hasConcept C127413603 @default.
- W2808657737 hasConcept C152124472 @default.
- W2808657737 hasConcept C153180895 @default.
- W2808657737 hasConcept C154945302 @default.
- W2808657737 hasConcept C164226766 @default.
- W2808657737 hasConcept C176217482 @default.
- W2808657737 hasConcept C21547014 @default.
- W2808657737 hasConcept C33923547 @default.
- W2808657737 hasConcept C41008148 @default.
- W2808657737 hasConcept C41608201 @default.
- W2808657737 hasConcept C5274069 @default.
- W2808657737 hasConcept C73555534 @default.
- W2808657737 hasConcept C79337645 @default.
- W2808657737 hasConcept C81917197 @default.
- W2808657737 hasConcept C93959086 @default.
- W2808657737 hasConceptScore W2808657737C103278499 @default.
- W2808657737 hasConceptScore W2808657737C111919701 @default.
- W2808657737 hasConceptScore W2808657737C114614502 @default.
- W2808657737 hasConceptScore W2808657737C115961682 @default.
- W2808657737 hasConceptScore W2808657737C119857082 @default.
- W2808657737 hasConceptScore W2808657737C124101348 @default.
- W2808657737 hasConceptScore W2808657737C127413603 @default.
- W2808657737 hasConceptScore W2808657737C152124472 @default.
- W2808657737 hasConceptScore W2808657737C153180895 @default.
- W2808657737 hasConceptScore W2808657737C154945302 @default.
- W2808657737 hasConceptScore W2808657737C164226766 @default.
- W2808657737 hasConceptScore W2808657737C176217482 @default.
- W2808657737 hasConceptScore W2808657737C21547014 @default.
- W2808657737 hasConceptScore W2808657737C33923547 @default.
- W2808657737 hasConceptScore W2808657737C41008148 @default.
- W2808657737 hasConceptScore W2808657737C41608201 @default.
- W2808657737 hasConceptScore W2808657737C5274069 @default.
- W2808657737 hasConceptScore W2808657737C73555534 @default.
- W2808657737 hasConceptScore W2808657737C79337645 @default.
- W2808657737 hasConceptScore W2808657737C81917197 @default.
- W2808657737 hasConceptScore W2808657737C93959086 @default.
- W2808657737 hasLocation W28086577371 @default.
- W2808657737 hasOpenAccess W2808657737 @default.
- W2808657737 hasPrimaryLocation W28086577371 @default.
- W2808657737 hasRelatedWork W1560498978 @default.
- W2808657737 hasRelatedWork W1972381050 @default.
- W2808657737 hasRelatedWork W2122407924 @default.
- W2808657737 hasRelatedWork W2318151098 @default.
- W2808657737 hasRelatedWork W2354434770 @default.
- W2808657737 hasRelatedWork W2379604828 @default.
- W2808657737 hasRelatedWork W2399400609 @default.
- W2808657737 hasRelatedWork W2495338271 @default.
- W2808657737 hasRelatedWork W2603836689 @default.
- W2808657737 hasRelatedWork W2734734306 @default.
- W2808657737 isParatext "false" @default.
- W2808657737 isRetracted "false" @default.
- W2808657737 magId "2808657737" @default.
- W2808657737 workType "article" @default.