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.
Scheda prodotto non validato
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo
Titolo: | Pose-Aware Face Recognition in the Wild | |
Autori: | MASI, IACOPO (Primo) | |
Data di pubblicazione: | 2016 | |
Serie: | ||
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 |