Pose-invariant face recognition via feature-space pose frontalization

TL;DR

This paper introduces a novel feature-space pose frontalization method for face recognition that improves accuracy in recognizing faces across different poses, outperforming existing techniques on multiple benchmarks.

Contribution

A new feature space pose frontalization module (FSPFM) and a training paradigm with pre-training and attention-guided fine-tuning are proposed for pose-invariant face recognition.

Findings

Outperforms state-of-the-art in pose-invariant face recognition

Maintains high performance in standard face recognition scenarios

Validated on five popular benchmarks

Abstract

Pose-invariant face recognition has become a challenging problem for modern AI-based face recognition systems. It aims at matching a profile face captured in the wild with a frontal face registered in a database. Existing methods perform face frontalization via either generative models or learning a pose robust feature representation. In this paper, a new method is presented to perform face frontalization and recognition within the feature space. First, a novel feature space pose frontalization module (FSPFM) is proposed to transform profile images with arbitrary angles into frontal counterparts. Second, a new training paradigm is proposed to maximize the potential of FSPFM and boost its performance. The latter consists of a pre-training and an attention-guided fine-tuning stage. Moreover, extensive experiments have been conducted on five popular face recognition benchmarks. Results show that not only our method outperforms the state-of-the-art in the pose-invariant face recognition task but also maintains superior performance in other standard scenarios.