A multi-task meta-learner-based ensemble for robust facial expression recognition in-the-wild.

Facial expression recognition is a topic of significant interest in affective computing. However, prior datasets and studies have primarily focused on recognizing facial expressions in controlled environments, limiting their generalizability to realistic context. Thus, despite recent advancements, recognizing facial expressions accurately in wild scenarios remains a challenging task. In this work, we propose an ensemble model based on multi-task meta-learner that utilizes a pool of CNN classifiers while dynamically selecting and fusing the optimal ensemble in order to recognize facial expressions more effectively in the wild. The suggested scheme leverages the output probabilities of base learners as meta-features, and integrates multi-label classification into dynamic ensemble selection. As best as we know, this is the first investigation of multi-task learning at the meta-learning level in the context of facial expression recognition. In particular, we introduce an effective meta-learner that combines the strengths of stacking and dynamic ensemble selection. The proposed approach has been evaluated exhaustively on several challenging datasets; including RAF-DB, FER2013, and FERPlus; and the obtained results demonstrate that the ensemble CNN outperforms individual CNN models consistently, while achieving high performance across all datasets. We further demonstrate the generalizability of the proposed approach by performing cross-dataset evaluation. [ABSTRACT FROM AUTHOR]