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

Title
Learning Pose-Aware Models for Pose-Invariant Face Recognition in the Wild
Authors
김강건Iacopo MasiFeng-Ju ChangJongmoo ChoiShai HarelJungyeon KimJatuporn LeksutStephen RawlsYue WuTal HassnerWael AbdAlmageedGerard MedioniLouis-Philippe MorencyPrem NatarajanRam Nevatia
Keywords
Face recognition; Convolutional neural networks; Pose-aware models
Issue Date
2019-02
Publisher
IEEE transactions on pattern analysis and machine intelligence
Citation
VOL 41, NO 2-393
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].
URI
http://pubs.kist.re.kr/handle/201004/69002
ISSN
0162-8828
Appears in Collections:
KIST Publication > Article
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE