Pose-Aware Face Recognition in the Wild

We propose a method to push the frontiers of unconstrained face recognition in the wild, focusing on the problem of extreme pose variations. As opposed to current techniques which either expect a single model to learn pose invariance through massive amounts of training data, or which normalize images to a single frontal pose, our method explicitly tackles pose variation by using multiple pose-specific models and rendered face images. We leverage deep Convolutional Neural Networks (CNNs) to learn discriminative representations we call Pose-Aware Models (PAMs) using 500K images from the CASIA WebFace dataset. We present a comparative evaluation on the new IARPA Janus Benchmark A (IJB-A) and PIPA datasets. On these datasets PAMs achieve remarkably better performance than commercial products and surprisingly also outperform methods that are specifically fine-tuned on the target dataset.

Pose-Aware Face Recognition in the Wild / Masi, I; Rawls, Stephen; Medioni, Gerard; Natarajan, Prem. - (2016). ((Intervento presentato al convegno Computer Vision and Pattern Recognition tenutosi a Las Vegas.

Titolo: Pose-Aware Face Recognition in the Wild
Autori: 
MASI, IACOPO (Primo)
mostra contributor esterni 
Data di pubblicazione: 2016
Serie: 
IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION  
Citazione: Pose-Aware Face Recognition in the Wild / Masi, I; Rawls, Stephen; Medioni, Gerard; Natarajan, Prem. - (2016). ((Intervento presentato al convegno Computer Vision and Pattern Recognition tenutosi a Las Vegas.
Handle: http://hdl.handle.net/11573/1458952
Appartiene alla tipologia:04b Atto di convegno in volume

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.
 
 
 
Powered by IRIS-about IRIS-Utilizzo dei cookie
Logo CINECA  Copyright © 2022