Abstract. Nowadays, the trend of the latest research in face recognition model shows that “the complex - the better” paradigm can be directly applied to these systems, whose accuracy effectively depends on both a large number of well-trained parameters and a complex functional structure. If this approach is sustainable for an offline processing on a consumer PC, it is far less appealing in the mobile environment, where processing power, as well as a high amount of onboard RAM could not be available. The distillation technique, applied on the cumbersome dlib-resnet-v1 face recognition model results in a lighter version that, while maintaining a comparable accuracy, can achieve a faster processing rate (>10x) and a lower memory occupation (1/6). The final model has been implemented on a single board PC, also using a neural hardware accelerator

A Fast Face Recognition CNN Obtained by Distillation

De Bortoli, Luca;Guzzi, F.
;
Marsi, S.;Carrato, S.;Ramponi, G.
2019-01-01

Abstract

Abstract. Nowadays, the trend of the latest research in face recognition model shows that “the complex - the better” paradigm can be directly applied to these systems, whose accuracy effectively depends on both a large number of well-trained parameters and a complex functional structure. If this approach is sustainable for an offline processing on a consumer PC, it is far less appealing in the mobile environment, where processing power, as well as a high amount of onboard RAM could not be available. The distillation technique, applied on the cumbersome dlib-resnet-v1 face recognition model results in a lighter version that, while maintaining a comparable accuracy, can achieve a faster processing rate (>10x) and a lower memory occupation (1/6). The final model has been implemented on a single board PC, also using a neural hardware accelerator
2019
978-3-030-37277-4
https://www.springer.com/gp/book/9783030372767
File in questo prodotto:
File Dimensione Formato  
cover.toc,capitolo.pdf

Accesso chiuso

Tipologia: Documento in Versione Editoriale
Licenza: Copyright Editore
Dimensione 1.62 MB
Formato Adobe PDF
1.62 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11368/2967867
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact