# Tree-gated Deep Regressor Ensemble For Face Alignment In The Wild

## TL;DR

This paper introduces a novel ensemble of deep regressors with a tree-structured gating mechanism to improve face alignment robustness in unconstrained, real-world images, outperforming existing methods.

## Contribution

It proposes a tree-gated deep regressor ensemble for face alignment, enhancing robustness to in-the-wild variations over single regressors.

## Key findings

- Outperforms state-of-the-art face alignment methods on challenging datasets.
- Demonstrates robustness to pose, expression, illumination, and occlusion variations.
- Effective adaptive weighting scheme improves alignment accuracy.

## Abstract

Face alignment consists in aligning a shape model on a face in an image. It is an active domain in computer vision as it is a preprocessing for applications like facial expression recognition, face recognition and tracking, face animation, etc. Current state-of-the-art methods already perform well on "easy" datasets, i.e. those that present moderate variations in head pose, expression, illumination or partial occlusions, but may not be robust to "in-the-wild" data. In this paper, we address this problem by using an ensemble of deep regressors instead of a single large regressor. Furthermore, instead of averaging the outputs of each regressor, we propose an adaptive weighting scheme that uses a tree-structured gate. Experiments on several challenging face datasets demonstrate that our approach outperforms the state-of-the-art methods.