GoDP: Globally optimized dual pathway system for facial landmark localization in-the-wild

TL;DR

GoDP introduces a globally optimized dual-pathway deep architecture for facial landmark localization that outperforms existing cascaded regression methods in challenging in-the-wild scenarios.

Contribution

This work presents a novel end-to-end deep architecture that directly identifies facial landmarks without high-level inference or complex cascades.

Findings

Achieves 1.84 NME on AFLW, outperforming 3DDFA by 61.8%.

Improves face identification rank-1 rate by 44.2% over Dlib.

Outperforms state-of-the-art cascaded regression methods.

Abstract

Facial landmark localization is a fundamental module for pose-invariant face recognition. The most common approach for facial landmark detection is cascaded regression, which is composed of two steps: feature extraction and facial shape regression. Recent methods employ deep convolutional networks to extract robust features for each step, while the whole system could be regarded as a deep cascaded regression architecture. In this work, instead of employing a deep regression network, a Globally Optimized Dual-Pathway (GoDP) deep architecture is proposed to identify the target pixels through solving a cascaded pixel labeling problem without resorting to high-level inference models or complex stacked architecture. The proposed end-to-end system relies on distance-aware softmax functions and dual-pathway proposal-refinement architecture. Results show that it outperforms the state-of-the-art cascaded regression-based methods on multiple in-the-wild face alignment databases. The model achieves 1.84 normalized mean error (NME) on the AFLW database, which outperforms 3DDFA by 61.8%. Experiments on face identification demonstrate that GoDP, coupled with DPM-headhunter, is able to improve rank-1 identification rate by 44.2% compared to Dlib toolbox on a challenging database.

Full text

See pages 1-last of rebutal_1020.pdf