Matches in SemOpenAlex for { <https://semopenalex.org/work/W2999313566> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2999313566 endingPage "156" @default.
- W2999313566 startingPage "144" @default.
- W2999313566 abstract "Face recognition is an important task in both academia and industry. With the development of deep convolutional neural networks, many deep face recognition methods have been proposed and have achieved remarkable results. However, these methods show great diversity among their datasets, network architectures, loss functions, and parameter learning strategies. For those who want to apply these technologies to establish a deep face recognition system, it is bewildering to evaluate which improvements are more suitable and effective. This study systematically summarizes and evaluates the state-of-the-art face recognition methods. However, unlike general reviews, on the basis of a survey, this study presents a comprehensive evaluation framework and measures the effects of multifarious settings in five components, including data augmentation, network architecture, loss function, network training, and model compression. Based on the experimental results, the influences of these five components on the deep face recognition are summarized. In terms of the datasets, a high sample-identity ratio is conducive to generalization, but it leads to increased difficulty for the training to converge. For the network architecture, deep ResNet has an advantage over other designs. Various normalization operations in the network are also necessary. For the loss function, whose performance is closely related to network design and training conditions. The angle-margin loss has a higher upper bound performance, but the traditional Euclidean-margin loss has a stable performance in limited training condition and shallower network. In terms of the training strategy, the step-declining learning rate and large batch size are recommended for recognition tasks. Furthermore, this study compares several popular model compression methods and shows that MobileNet has advantages over the others in terms of both compression ratio and robustness. Finally, a detailed list of recommended settings is provided." @default.
- W2999313566 created "2020-01-23" @default.
- W2999313566 creator A5010299064 @default.
- W2999313566 creator A5017499947 @default.
- W2999313566 creator A5027475930 @default.
- W2999313566 creator A5056627511 @default.
- W2999313566 date "2020-05-01" @default.
- W2999313566 modified "2023-10-14" @default.
- W2999313566 title "Systematic evaluation of deep face recognition methods" @default.
- W2999313566 cites W1951319388 @default.
- W2999313566 cites W2342709286 @default.
- W2999313566 cites W2470717811 @default.
- W2999313566 cites W2513203649 @default.
- W2999313566 cites W2580365077 @default.
- W2999313566 cites W2899768658 @default.
- W2999313566 cites W2900681352 @default.
- W2999313566 cites W2905227840 @default.
- W2999313566 cites W2918254569 @default.
- W2999313566 cites W2963671154 @default.
- W2999313566 cites W2969985801 @default.
- W2999313566 cites W3101998545 @default.
- W2999313566 doi "https://doi.org/10.1016/j.neucom.2020.01.023" @default.
- W2999313566 hasPublicationYear "2020" @default.
- W2999313566 type Work @default.
- W2999313566 sameAs 2999313566 @default.
- W2999313566 citedByCount "13" @default.
- W2999313566 countsByYear W29993135662020 @default.
- W2999313566 countsByYear W29993135662022 @default.
- W2999313566 countsByYear W29993135662023 @default.
- W2999313566 crossrefType "journal-article" @default.
- W2999313566 hasAuthorship W2999313566A5010299064 @default.
- W2999313566 hasAuthorship W2999313566A5017499947 @default.
- W2999313566 hasAuthorship W2999313566A5027475930 @default.
- W2999313566 hasAuthorship W2999313566A5056627511 @default.
- W2999313566 hasConcept C108583219 @default.
- W2999313566 hasConcept C119857082 @default.
- W2999313566 hasConcept C134306372 @default.
- W2999313566 hasConcept C136886441 @default.
- W2999313566 hasConcept C144024400 @default.
- W2999313566 hasConcept C153180895 @default.
- W2999313566 hasConcept C154945302 @default.
- W2999313566 hasConcept C177148314 @default.
- W2999313566 hasConcept C19165224 @default.
- W2999313566 hasConcept C193415008 @default.
- W2999313566 hasConcept C31510193 @default.
- W2999313566 hasConcept C33923547 @default.
- W2999313566 hasConcept C38652104 @default.
- W2999313566 hasConcept C41008148 @default.
- W2999313566 hasConcept C50644808 @default.
- W2999313566 hasConcept C774472 @default.
- W2999313566 hasConcept C81363708 @default.
- W2999313566 hasConceptScore W2999313566C108583219 @default.
- W2999313566 hasConceptScore W2999313566C119857082 @default.
- W2999313566 hasConceptScore W2999313566C134306372 @default.
- W2999313566 hasConceptScore W2999313566C136886441 @default.
- W2999313566 hasConceptScore W2999313566C144024400 @default.
- W2999313566 hasConceptScore W2999313566C153180895 @default.
- W2999313566 hasConceptScore W2999313566C154945302 @default.
- W2999313566 hasConceptScore W2999313566C177148314 @default.
- W2999313566 hasConceptScore W2999313566C19165224 @default.
- W2999313566 hasConceptScore W2999313566C193415008 @default.
- W2999313566 hasConceptScore W2999313566C31510193 @default.
- W2999313566 hasConceptScore W2999313566C33923547 @default.
- W2999313566 hasConceptScore W2999313566C38652104 @default.
- W2999313566 hasConceptScore W2999313566C41008148 @default.
- W2999313566 hasConceptScore W2999313566C50644808 @default.
- W2999313566 hasConceptScore W2999313566C774472 @default.
- W2999313566 hasConceptScore W2999313566C81363708 @default.
- W2999313566 hasFunder F4320309612 @default.
- W2999313566 hasFunder F4320321001 @default.
- W2999313566 hasFunder F4320335787 @default.
- W2999313566 hasLocation W29993135661 @default.
- W2999313566 hasOpenAccess W2999313566 @default.
- W2999313566 hasPrimaryLocation W29993135661 @default.
- W2999313566 hasRelatedWork W1991269640 @default.
- W2999313566 hasRelatedWork W2517027266 @default.
- W2999313566 hasRelatedWork W2731899572 @default.
- W2999313566 hasRelatedWork W3091976719 @default.
- W2999313566 hasRelatedWork W3116150086 @default.
- W2999313566 hasRelatedWork W3133861977 @default.
- W2999313566 hasRelatedWork W4200173597 @default.
- W2999313566 hasRelatedWork W4312417841 @default.
- W2999313566 hasRelatedWork W4321369474 @default.
- W2999313566 hasRelatedWork W2508457823 @default.
- W2999313566 hasVolume "388" @default.
- W2999313566 isParatext "false" @default.
- W2999313566 isRetracted "false" @default.
- W2999313566 magId "2999313566" @default.
- W2999313566 workType "article" @default.