Self-Reinforced Cascaded Regression for Face Alignment

TL;DR

This paper introduces a self-reinforced cascaded regression method for face alignment that iteratively improves training data quality by evaluating local appearance and global geometry consistency, enhancing accuracy and robustness.

Contribution

It proposes a novel self-reinforced strategy that expands and refines training examples for cascaded regression using local and global face geometry validation.

Findings

Improved face alignment accuracy on benchmark datasets.

Effective example selection from small initial datasets.

Enhanced robustness of cascaded regression models.

Abstract

Cascaded regression is prevailing in face alignment thanks to its accuracy and robustness, but typically demands manually annotated examples having low discrepancy between shape-indexed features and shape updates. In this paper, we propose a self-reinforced strategy that iteratively expands the quantity and improves the quality of training examples, thus upgrading the performance of cascaded regression itself. The reinforced term evaluates the example quality upon the consistence on both local appearance and global geometry of human faces, and constitutes the example evolution by the philosophy of "survival of the fittest". We train a set of discriminative classifiers, each associated with one landmark label, to prune those examples with inconsistent local appearance, and further validate the geometric relationship among groups of labeled landmarks against the common global geometry derived from a projective invariant. We embed this generic strategy into typical cascaded regressions, and the alignment results on several benchmark data sets demonstrate its effectiveness to predict good examples starting from a small subset.