Generative Adversarial Stacked Autoencoders for Facial Pose Normalization and Emotion Recognition
This addresses the problem of pose variation in facial emotion recognition for computer vision applications, representing an incremental improvement with novel training and architectural components.
The paper tackles facial emotion recognition by normalizing facial poses up to ±60 degrees to 0 degrees using a Generative Adversarial Stacked Autoencoder, achieving state-of-the-art performance on multiple datasets including in-the-wild corpora.
In this work, we propose a novel Generative Adversarial Stacked Autoencoder that learns to map facial expressions, with up to plus or minus 60 degrees, to an illumination invariant facial representation of 0 degrees. We accomplish this by using a novel convolutional layer that exploits both local and global spatial information, and a convolutional layer with a reduced number of parameters that exploits facial symmetry. Furthermore, we introduce a generative adversarial gradual greedy layer-wise learning algorithm designed to train Adversarial Autoencoders in an efficient and incremental manner. We demonstrate the efficiency of our method and report state-of-the-art performance on several facial emotion recognition corpora, including one collected in the wild.