Face recognition capabilities have recently made extraordinary leaps. Though this progress is at least partially due to ballooning training set sizes – huge numbers of face images downloaded and labeled for identity – it is not clear if the formidable task of collecting so many images is truly necessary. We propose a far more accessible means of increasing training data sizes for face recognition systems: Domain specific data augmentation. We describe novel methods of enriching an existing dataset with important facial appearance variations by manipulating the faces it contains. This synthesis is also used when matching query images represented by standard convolutional neural networks. The effect of training and testing with synthesized images is tested on the LFW and IJB-A (verification and identification) benchmarks and Janus CS2.

Do We Really Need to Collect Millions of Faces for Effective Face Recognition? / Masi, I; Tran Anh, Tuan; Hassner, Tal; Leksut Jatuporn, Toy; Medioni, Gerard. - (2016), pp. 579-596. (Intervento presentato al convegno European Conference on Computer Vision (ECCV 2016) tenutosi a Amsterdam, Netherlands) [10.1007/978-3-319-46454-1_35].

Do We Really Need to Collect Millions of Faces for Effective Face Recognition?

Masi I;
2016

Abstract

Face recognition capabilities have recently made extraordinary leaps. Though this progress is at least partially due to ballooning training set sizes – huge numbers of face images downloaded and labeled for identity – it is not clear if the formidable task of collecting so many images is truly necessary. We propose a far more accessible means of increasing training data sizes for face recognition systems: Domain specific data augmentation. We describe novel methods of enriching an existing dataset with important facial appearance variations by manipulating the faces it contains. This synthesis is also used when matching query images represented by standard convolutional neural networks. The effect of training and testing with synthesized images is tested on the LFW and IJB-A (verification and identification) benchmarks and Janus CS2.
2016
European Conference on Computer Vision (ECCV 2016)
face recognition, deep learning, face analysis
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Do We Really Need to Collect Millions of Faces for Effective Face Recognition? / Masi, I; Tran Anh, Tuan; Hassner, Tal; Leksut Jatuporn, Toy; Medioni, Gerard. - (2016), pp. 579-596. (Intervento presentato al convegno European Conference on Computer Vision (ECCV 2016) tenutosi a Amsterdam, Netherlands) [10.1007/978-3-319-46454-1_35].
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

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/11573/1458962
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 185
  • ???jsp.display-item.citation.isi??? 186
social impact