We propose a method designed to push the frontiers of unconstrained face recognition in the wild with an emphasis on extreme out-of-plane pose variations. Existing methods either expect a single model to learn pose invariance by training on massive amounts of data or else normalize images by aligning faces to a single frontal pose. Contrary to these, our method is designed to explicitly tackle pose variations. Our proposed Pose-Aware Models (PAM) process a face image using several pose-specific, deep convolutional neural networks (CNN). 3D rendering is used to synthesize multiple face poses from input images to both train these models and to provide additional robustness to pose variations at test time. Our paper presents an extensive analysis of the IARPA Janus Benchmark A (IJB-A), evaluating the effects that landmark detection accuracy, CNN layer selection, and pose model selection all have on the performance of the recognition pipeline. It further provides comparative evaluations on IJB-A and the PIPA dataset. These tests show that our approach outperforms existing methods, even surprisingly matching the accuracy of methods that were specifically fine-tuned to the target dataset. Parts of this work previously appeared in [1] and [2].

Learning Pose-Aware Models for Pose-Invariant Face Recognition in the Wild / Masi, I.; Chang, F. -J.; Choi, J.; Harel, S.; Kim, J.; Kim, K.; Leksut, J.; Rawls, S.; Wu, Y.; Hassner, T.; Abdalmageed, W.; Medioni, G.; Morency, L. -P.; Natarajan, P.; Nevatia, R.. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - 41:2(2018), pp. 379-393. [10.1109/TPAMI.2018.2792452]

Learning Pose-Aware Models for Pose-Invariant Face Recognition in the Wild

Masi I.
Primo
Writing – Original Draft Preparation
;
2018

Abstract

We propose a method designed to push the frontiers of unconstrained face recognition in the wild with an emphasis on extreme out-of-plane pose variations. Existing methods either expect a single model to learn pose invariance by training on massive amounts of data or else normalize images by aligning faces to a single frontal pose. Contrary to these, our method is designed to explicitly tackle pose variations. Our proposed Pose-Aware Models (PAM) process a face image using several pose-specific, deep convolutional neural networks (CNN). 3D rendering is used to synthesize multiple face poses from input images to both train these models and to provide additional robustness to pose variations at test time. Our paper presents an extensive analysis of the IARPA Janus Benchmark A (IJB-A), evaluating the effects that landmark detection accuracy, CNN layer selection, and pose model selection all have on the performance of the recognition pipeline. It further provides comparative evaluations on IJB-A and the PIPA dataset. These tests show that our approach outperforms existing methods, even surprisingly matching the accuracy of methods that were specifically fine-tuned to the target dataset. Parts of this work previously appeared in [1] and [2].
2018
CNN; Face recognition; pose-aware
01 Pubblicazione su rivista::01a Articolo in rivista
Learning Pose-Aware Models for Pose-Invariant Face Recognition in the Wild / Masi, I.; Chang, F. -J.; Choi, J.; Harel, S.; Kim, J.; Kim, K.; Leksut, J.; Rawls, S.; Wu, Y.; Hassner, T.; Abdalmageed, W.; Medioni, G.; Morency, L. -P.; Natarajan, P.; Nevatia, R.. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - 41:2(2018), pp. 379-393. [10.1109/TPAMI.2018.2792452]
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/11573/1455264
 Attenzione

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

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 69
  • ???jsp.display-item.citation.isi??? 50
social impact