Learning Disentangled Expression Representations from Facial Images
This work addresses the challenge of limited labeled data for facial expression recognition in unconstrained scenarios, representing an incremental improvement over existing methods.
The paper tackled the problem of learning disentangled representations for facial images to improve expression recognition, achieving a state-of-the-art accuracy of 60.53% on the AffectNet dataset without using additional data.
Face images are subject to many different factors of variation, especially in unconstrained in-the-wild scenarios. For most tasks involving such images, e.g. expression recognition from video streams, having enough labeled data is prohibitively expensive. One common strategy to tackle such a problem is to learn disentangled representations for the different factors of variation of the observed data using adversarial learning. In this paper, we use a formulation of the adversarial loss to learn disentangled representations for face images. The used model facilitates learning on single-task datasets and improves the state-of-the-art in expression recognition with an accuracy of60.53%on the AffectNetdataset, without using any additional data.