Facial Expression Representation Learning by Synthesizing Expression Images

TL;DR

This paper introduces DE-GAN, a novel generative adversarial network that explicitly disentangles facial expression features from identity, improving facial expression recognition by synthesizing high-quality expression images.

Contribution

The paper proposes a new disentangled representation learning method using DE-GAN that explicitly separates expression from identity features for better FER performance.

Findings

Achieves comparable or superior accuracy on CK+, MMI, Oulu-CASIA datasets.

Produces high-quality synthesized expression images.

Effectively disentangles expression features from identity.

Abstract

Representations used for Facial Expression Recognition (FER) usually contain expression information along with identity features. In this paper, we propose a novel Disentangled Expression learning-Generative Adversarial Network (DE-GAN) which combines the concept of disentangled representation learning with residue learning to explicitly disentangle facial expression representation from identity information. In this method the facial expression representation is learned by reconstructing an expression image employing an encoder-decoder based generator. Unlike previous works using only expression residual learning for facial expression recognition, our method learns the disentangled expression representation along with the expressive component recorded by the encoder of DE-GAN. In order to improve the quality of synthesized expression images and the effectiveness of the learned disentangled expression representation, expression and identity classification is performed by the discriminator of DE-GAN. Experiments performed on widely used datasets (CK+, MMI, Oulu-CASIA) show that the proposed technique produces comparable or better results than state-of-the-art methods.