Do Deep Neural Networks Learn Facial Action Units When Doing Expression Recognition?

TL;DR

This paper demonstrates that CNNs can achieve state-of-the-art performance in facial expression recognition and reveals that they learn to recognize facial action units, providing insights into what features influence their predictions.

Contribution

The study introduces a method to interpret CNNs in facial expression recognition, showing they learn facial action units and achieving top performance on benchmark datasets.

Findings

CNNs achieve state-of-the-art results on CK+ and TFD datasets.

Visualizations show CNN neurons respond to facial action units.

FAU labels confirm CNN features align with facial movements.

Abstract

Despite being the appearance-based classifier of choice in recent years, relatively few works have examined how much convolutional neural networks (CNNs) can improve performance on accepted expression recognition benchmarks and, more importantly, examine what it is they actually learn. In this work, not only do we show that CNNs can achieve strong performance, but we also introduce an approach to decipher which portions of the face influence the CNN's predictions. First, we train a zero-bias CNN on facial expression data and achieve, to our knowledge, state-of-the-art performance on two expression recognition benchmarks: the extended Cohn-Kanade (CK+) dataset and the Toronto Face Dataset (TFD). We then qualitatively analyze the network by visualizing the spatial patterns that maximally excite different neurons in the convolutional layers and show how they resemble Facial Action Units (FAUs). Finally, we use the FAU labels provided in the CK+ dataset to verify that the FAUs observed in our filter visualizations indeed align with the subject's facial movements.