Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian

TL;DR

This paper introduces an anisotropic spherical Gaussian-based label distribution learning method for facial pose estimation, addressing bias issues and enabling flexible distribution parameters, resulting in state-of-the-art performance.

Contribution

It proposes a novel LDL approach using anisotropic spherical Gaussian distributions with learnable parameters, improving bias correction and model flexibility.

Findings

Achieves new state-of-the-art results on AFLW2000 and BIWI datasets.

Effectively reduces bias in pose estimation.

Enables sample-specific distribution parameter learning.

Abstract

Facial pose estimation refers to the task of predicting face orientation from a single RGB image. It is an important research topic with a wide range of applications in computer vision. Label distribution learning (LDL) based methods have been recently proposed for facial pose estimation, which achieve promising results. However, there are two major issues in existing LDL methods. First, the expectations of label distributions are biased, leading to a biased pose estimation. Second, fixed distribution parameters are applied for all learning samples, severely limiting the model capability. In this paper, we propose an Anisotropic Spherical Gaussian (ASG)-based LDL approach for facial pose estimation. In particular, our approach adopts the spherical Gaussian distribution on a unit sphere which constantly generates unbiased expectation. Meanwhile, we introduce a new loss function that allows the network to learn the distribution parameter for each learning sample flexibly. Extensive experimental results show that our method sets new state-of-the-art records on AFLW2000 and BIWI datasets.