Tree-gated Deep Mixture-of-Experts For Pose-robust Face Alignment

10/21/2019
by   Estephe Arnaud, et al.
15

Face alignment consists of aligning a shape model on a face image. It is an active domain in computer vision as it is a preprocessing for a number of face analysis and synthesis applications. Current state-of-the-art methods already perform well on "easy" datasets, with moderate head pose variations, but may not be robust for "in-the-wild" data with poses up to 90. In order to increase robustness to an ensemble of factors of variations (e.g. head pose or occlusions), a given layer (e.g. a regressor or an upstream CNN layer) can be replaced by a Mixture of Experts (MoE) layer that uses an ensemble of experts instead of a single one. The weights of this mixture can be learned as gating functions to jointly learn the experts and the corresponding weights. In this paper, we propose to use tree-structured gates which allows a hierarchical weighting of the experts (Tree-MoE). We investigate the use of Tree-MoE layers in different contexts in the frame of face alignment with cascaded regression, firstly for emphasizing relevant, more specialized feature extractors depending of a high-level semantic information such as head pose (Pose-Tree-MoE), and secondly as an overall more robust regression layer. We perform extensive experiments on several challenging face alignment datasets, demonstrating that our approach outperforms the state-of-the-art methods.

READ FULL TEXT

page 2

page 5

page 9

page 13

research
07/07/2019

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

Face alignment consists in aligning a shape model on a face in an image....
research
11/13/2015

Robust Face Alignment Using a Mixture of Invariant Experts

Face alignment, which is the task of finding the locations of a set of f...
research
06/06/2021

SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction

Three-dimensional face dense alignment and reconstruction in the wild is...
research
02/04/2022

Multi-task head pose estimation in-the-wild

We present a deep learning-based multi-task approach for head pose estim...
research
03/31/2016

Robust Head-Pose Estimation Based on Partially-Latent Mixture of Linear Regressions

Head-pose estimation has many applications, such as social event analysi...
research
07/23/2018

Identity Preserving Face Completion for Large Ocular Region Occlusion

We present a novel deep learning approach to synthesize complete face im...
research
07/19/2017

Pose-Invariant Face Alignment with a Single CNN

Face alignment has witnessed substantial progress in the last decade. On...

Please sign up or login with your details

Forgot password? Click here to reset