Matches in SemOpenAlex for { <https://semopenalex.org/work/W3082065950> ?p ?o ?g. }
- W3082065950 abstract "Gait is a popular biometric pattern used for identifying people based on their way of walking. Traditionally, gait recognition approaches based on deep learning are trained using the whole training dataset. In fact, if new data (classes, view-points, walking conditions, etc.) need to be included, it is necessary to re-train again the model with old and new data samples. In this paper, we propose iLGaCo, the first incremental learning approach of covariate factors for gait recognition, where the deep model can be updated with new information without re-training it from scratch by using the whole dataset. Instead, our approach performs a shorter training process with the new data and a small subset of previous samples. This way, our model learns new information while retaining previous knowledge. We evaluate iLGaCo on CASIA-B dataset in two incremental ways: adding new view-points and adding new walking conditions. In both cases, our results are close to the classical `training-from-scratch' approach, obtaining a marginal drop in accuracy ranging from 0.2% to 1.2%, what shows the efficacy of our approach. In addition, the comparison of iLGaCo with other incremental learning methods, such as LwF and iCarl, shows a significant improvement in accuracy, between 6% and 15% depending on the experiment." @default.
- W3082065950 created "2020-09-08" @default.
- W3082065950 creator A5005774263 @default.
- W3082065950 creator A5029567783 @default.
- W3082065950 creator A5030831939 @default.
- W3082065950 creator A5035928355 @default.
- W3082065950 creator A5041004091 @default.
- W3082065950 creator A5042354417 @default.
- W3082065950 date "2020-08-31" @default.
- W3082065950 modified "2023-09-30" @default.
- W3082065950 title "iLGaCo: Incremental Learning of Gait Covariate Factors" @default.
- W3082065950 cites W1467353089 @default.
- W3082065950 cites W1557856703 @default.
- W3082065950 cites W1821462560 @default.
- W3082065950 cites W1862849385 @default.
- W3082065950 cites W1954814386 @default.
- W3082065950 cites W1997865285 @default.
- W3082065950 cites W2003574320 @default.
- W3082065950 cites W2032409772 @default.
- W3082065950 cites W2063626761 @default.
- W3082065950 cites W2104335344 @default.
- W3082065950 cites W2113839990 @default.
- W3082065950 cites W2138350282 @default.
- W3082065950 cites W2152914237 @default.
- W3082065950 cites W2185146746 @default.
- W3082065950 cites W2291015381 @default.
- W3082065950 cites W2293736741 @default.
- W3082065950 cites W2296629652 @default.
- W3082065950 cites W2322772590 @default.
- W3082065950 cites W2473930607 @default.
- W3082065950 cites W2474280151 @default.
- W3082065950 cites W2535110112 @default.
- W3082065950 cites W2557283755 @default.
- W3082065950 cites W2560647685 @default.
- W3082065950 cites W2884282566 @default.
- W3082065950 cites W2904399478 @default.
- W3082065950 cites W2926477959 @default.
- W3082065950 cites W2947461406 @default.
- W3082065950 cites W2948336998 @default.
- W3082065950 cites W2952677972 @default.
- W3082065950 cites W2960957522 @default.
- W3082065950 cites W2962966271 @default.
- W3082065950 cites W2963301258 @default.
- W3082065950 cites W2964189064 @default.
- W3082065950 cites W2964240787 @default.
- W3082065950 cites W2970971581 @default.
- W3082065950 cites W2977530922 @default.
- W3082065950 cites W2981864462 @default.
- W3082065950 cites W2997616834 @default.
- W3082065950 cites W3002177189 @default.
- W3082065950 cites W3005477560 @default.
- W3082065950 cites W3007168191 @default.
- W3082065950 cites W3010419530 @default.
- W3082065950 cites W3015331232 @default.
- W3082065950 cites W3103800629 @default.
- W3082065950 doi "https://doi.org/10.48550/arxiv.2008.13507" @default.
- W3082065950 hasPublicationYear "2020" @default.
- W3082065950 type Work @default.
- W3082065950 sameAs 3082065950 @default.
- W3082065950 citedByCount "0" @default.
- W3082065950 crossrefType "posted-content" @default.
- W3082065950 hasAuthorship W3082065950A5005774263 @default.
- W3082065950 hasAuthorship W3082065950A5029567783 @default.
- W3082065950 hasAuthorship W3082065950A5030831939 @default.
- W3082065950 hasAuthorship W3082065950A5035928355 @default.
- W3082065950 hasAuthorship W3082065950A5041004091 @default.
- W3082065950 hasAuthorship W3082065950A5042354417 @default.
- W3082065950 hasBestOaLocation W30820659501 @default.
- W3082065950 hasConcept C111919701 @default.
- W3082065950 hasConcept C115051666 @default.
- W3082065950 hasConcept C119043178 @default.
- W3082065950 hasConcept C119857082 @default.
- W3082065950 hasConcept C151800584 @default.
- W3082065950 hasConcept C153180895 @default.
- W3082065950 hasConcept C154945302 @default.
- W3082065950 hasConcept C184297639 @default.
- W3082065950 hasConcept C2780735816 @default.
- W3082065950 hasConcept C2781235140 @default.
- W3082065950 hasConcept C41008148 @default.
- W3082065950 hasConcept C71924100 @default.
- W3082065950 hasConcept C76155785 @default.
- W3082065950 hasConcept C98045186 @default.
- W3082065950 hasConcept C99508421 @default.
- W3082065950 hasConceptScore W3082065950C111919701 @default.
- W3082065950 hasConceptScore W3082065950C115051666 @default.
- W3082065950 hasConceptScore W3082065950C119043178 @default.
- W3082065950 hasConceptScore W3082065950C119857082 @default.
- W3082065950 hasConceptScore W3082065950C151800584 @default.
- W3082065950 hasConceptScore W3082065950C153180895 @default.
- W3082065950 hasConceptScore W3082065950C154945302 @default.
- W3082065950 hasConceptScore W3082065950C184297639 @default.
- W3082065950 hasConceptScore W3082065950C2780735816 @default.
- W3082065950 hasConceptScore W3082065950C2781235140 @default.
- W3082065950 hasConceptScore W3082065950C41008148 @default.
- W3082065950 hasConceptScore W3082065950C71924100 @default.
- W3082065950 hasConceptScore W3082065950C76155785 @default.
- W3082065950 hasConceptScore W3082065950C98045186 @default.
- W3082065950 hasConceptScore W3082065950C99508421 @default.
- W3082065950 hasLocation W30820659501 @default.
- W3082065950 hasOpenAccess W3082065950 @default.