Matches in SemOpenAlex for { <https://semopenalex.org/work/W3011837252> ?p ?o ?g. }
- W3011837252 abstract "This article aims to demonstrate the value of deep metric learning considering recent studies. Most existing studies are inspired by Siamese and Triplet networks that build a high-level representation of samples in separable linear space. The success and main idea of these networks is the ability to capture the similarity relationship between samples in the dataset. There are mainly three components: sampling method, loss function, and neural network architecture that determine the metric learning model. Improvement of these components is the main challenge for researchers. This article is a review and analysis of deep metric learning components." @default.
- W3011837252 created "2020-03-23" @default.
- W3011837252 creator A5003551354 @default.
- W3011837252 creator A5006464105 @default.
- W3011837252 date "2019-12-01" @default.
- W3011837252 modified "2023-09-26" @default.
- W3011837252 title "Analysis of Deep Metric Learning Approaches" @default.
- W3011837252 cites W1703179648 @default.
- W3011837252 cites W1869500417 @default.
- W3011837252 cites W1978590356 @default.
- W3011837252 cites W2021354639 @default.
- W3011837252 cites W2062112832 @default.
- W3011837252 cites W2076434944 @default.
- W3011837252 cites W2117239879 @default.
- W3011837252 cites W2127589108 @default.
- W3011837252 cites W2130556178 @default.
- W3011837252 cites W2138621090 @default.
- W3011837252 cites W2157364932 @default.
- W3011837252 cites W2412580962 @default.
- W3011837252 cites W2489805186 @default.
- W3011837252 cites W2497173630 @default.
- W3011837252 cites W2564853008 @default.
- W3011837252 cites W2591719913 @default.
- W3011837252 cites W2604164738 @default.
- W3011837252 cites W2679426462 @default.
- W3011837252 cites W2767325013 @default.
- W3011837252 cites W2891343776 @default.
- W3011837252 cites W2895347732 @default.
- W3011837252 cites W2910350028 @default.
- W3011837252 cites W2919115771 @default.
- W3011837252 cites W2962798895 @default.
- W3011837252 cites W2962918106 @default.
- W3011837252 cites W2963026686 @default.
- W3011837252 cites W2963466847 @default.
- W3011837252 cites W2963775347 @default.
- W3011837252 cites W2969656782 @default.
- W3011837252 cites W2969985801 @default.
- W3011837252 cites W2979329071 @default.
- W3011837252 cites W3099206234 @default.
- W3011837252 cites W566612420 @default.
- W3011837252 doi "https://doi.org/10.1109/atit49449.2019.9030440" @default.
- W3011837252 hasPublicationYear "2019" @default.
- W3011837252 type Work @default.
- W3011837252 sameAs 3011837252 @default.
- W3011837252 citedByCount "0" @default.
- W3011837252 crossrefType "proceedings-article" @default.
- W3011837252 hasAuthorship W3011837252A5003551354 @default.
- W3011837252 hasAuthorship W3011837252A5006464105 @default.
- W3011837252 hasConcept C103278499 @default.
- W3011837252 hasConcept C108583219 @default.
- W3011837252 hasConcept C115961682 @default.
- W3011837252 hasConcept C119857082 @default.
- W3011837252 hasConcept C124101348 @default.
- W3011837252 hasConcept C127413603 @default.
- W3011837252 hasConcept C134306372 @default.
- W3011837252 hasConcept C140779682 @default.
- W3011837252 hasConcept C154945302 @default.
- W3011837252 hasConcept C176217482 @default.
- W3011837252 hasConcept C17744445 @default.
- W3011837252 hasConcept C198043062 @default.
- W3011837252 hasConcept C199539241 @default.
- W3011837252 hasConcept C21547014 @default.
- W3011837252 hasConcept C2776359362 @default.
- W3011837252 hasConcept C33923547 @default.
- W3011837252 hasConcept C41008148 @default.
- W3011837252 hasConcept C50644808 @default.
- W3011837252 hasConcept C76155785 @default.
- W3011837252 hasConcept C94625758 @default.
- W3011837252 hasConcept C94915269 @default.
- W3011837252 hasConceptScore W3011837252C103278499 @default.
- W3011837252 hasConceptScore W3011837252C108583219 @default.
- W3011837252 hasConceptScore W3011837252C115961682 @default.
- W3011837252 hasConceptScore W3011837252C119857082 @default.
- W3011837252 hasConceptScore W3011837252C124101348 @default.
- W3011837252 hasConceptScore W3011837252C127413603 @default.
- W3011837252 hasConceptScore W3011837252C134306372 @default.
- W3011837252 hasConceptScore W3011837252C140779682 @default.
- W3011837252 hasConceptScore W3011837252C154945302 @default.
- W3011837252 hasConceptScore W3011837252C176217482 @default.
- W3011837252 hasConceptScore W3011837252C17744445 @default.
- W3011837252 hasConceptScore W3011837252C198043062 @default.
- W3011837252 hasConceptScore W3011837252C199539241 @default.
- W3011837252 hasConceptScore W3011837252C21547014 @default.
- W3011837252 hasConceptScore W3011837252C2776359362 @default.
- W3011837252 hasConceptScore W3011837252C33923547 @default.
- W3011837252 hasConceptScore W3011837252C41008148 @default.
- W3011837252 hasConceptScore W3011837252C50644808 @default.
- W3011837252 hasConceptScore W3011837252C76155785 @default.
- W3011837252 hasConceptScore W3011837252C94625758 @default.
- W3011837252 hasConceptScore W3011837252C94915269 @default.
- W3011837252 hasLocation W30118372521 @default.
- W3011837252 hasOpenAccess W3011837252 @default.
- W3011837252 hasPrimaryLocation W30118372521 @default.
- W3011837252 hasRelatedWork W10786582 @default.
- W3011837252 hasRelatedWork W13536281 @default.
- W3011837252 hasRelatedWork W1849215 @default.
- W3011837252 hasRelatedWork W309696 @default.
- W3011837252 hasRelatedWork W5331339 @default.
- W3011837252 hasRelatedWork W5879097 @default.
- W3011837252 hasRelatedWork W6680660 @default.