DeepCoder: Semi-parametric Variational Autoencoders for Automatic Facial Action Coding

TL;DR

DeepCoder introduces a semi-parametric VAE framework combining convolutional and Gaussian Process models to improve facial action unit intensity estimation, outperforming existing methods on benchmark datasets.

Contribution

It presents a novel semi-parametric VAE model that jointly learns hierarchical facial features and ordinal AU intensity classification, integrating parametric and non-parametric approaches.

Findings

DeepCoder outperforms state-of-the-art AU intensity estimation methods.

The model effectively captures hierarchical facial features.

It demonstrates robustness and improved accuracy on benchmark datasets.

Abstract

Human face exhibits an inherent hierarchy in its representations (i.e., holistic facial expressions can be encoded via a set of facial action units (AUs) and their intensity). Variational (deep) auto-encoders (VAE) have shown great results in unsupervised extraction of hierarchical latent representations from large amounts of image data, while being robust to noise and other undesired artifacts. Potentially, this makes VAEs a suitable approach for learning facial features for AU intensity estimation. Yet, most existing VAE-based methods apply classifiers learned separately from the encoded features. By contrast, the non-parametric (probabilistic) approaches, such as Gaussian Processes (GPs), typically outperform their parametric counterparts, but cannot deal easily with large amounts of data. To this end, we propose a novel VAE semi-parametric modeling framework, named DeepCoder, which combines the modeling power of parametric (convolutional) and nonparametric (ordinal GPs) VAEs, for joint learning of (1) latent representations at multiple levels in a task hierarchy1, and (2) classification of multiple ordinal outputs. We show on benchmark datasets for AU intensity estimation that the proposed DeepCoder outperforms the state-of-the-art approaches, and related VAEs and deep learning models.