Face Recognition Using Deep Multi-Pose Representations

TL;DR

This paper presents a face recognition system that uses multiple pose-specific deep learning models to improve accuracy across pose variations, achieving state-of-the-art results on benchmark datasets.

Contribution

The authors introduce a novel multi-pose deep learning representation that enhances face recognition performance by combining pose-specific CNN features and 3D pose rendering.

Findings

Outperforms state-of-the-art on IARPA's CS2 dataset

Achieves superior results on NIST's IJB-A in verification and identification

Demonstrates robustness to pose variations through ensemble of pose-specific features

Abstract

We introduce our method and system for face recognition using multiple pose-aware deep learning models. In our representation, a face image is processed by several pose-specific deep convolutional neural network (CNN) models to generate multiple pose-specific features. 3D rendering is used to generate multiple face poses from the input image. Sensitivity of the recognition system to pose variations is reduced since we use an ensemble of pose-specific CNN features. The paper presents extensive experimental results on the effect of landmark detection, CNN layer selection and pose model selection on the performance of the recognition pipeline. Our novel representation achieves better results than the state-of-the-art on IARPA's CS2 and NIST's IJB-A in both verification and identification (i.e. search) tasks.