Gaussian Process Domain Experts for Model Adaptation in Facial Behavior Analysis
This work addresses domain adaptation challenges in facial behavior analysis, offering a novel probabilistic method that is incremental but effective for improving classification accuracy across different views and subjects.
The paper tackles the problem of supervised domain adaptation for facial expression classification by introducing domain-specific Gaussian process experts, which condition target experts on multiple source experts and combine predictions based on confidence. The approach outperforms source and target classifiers and state-of-the-art methods, achieving strong results with as few as 30 target examples on MultiPIE and DISFA datasets.
We present a novel approach for supervised domain adaptation that is based upon the probabilistic framework of Gaussian processes (GPs). Specifically, we introduce domain-specific GPs as local experts for facial expression classification from face images. The adaptation of the classifier is facilitated in probabilistic fashion by conditioning the target expert on multiple source experts. Furthermore, in contrast to existing adaptation approaches, we also learn a target expert from available target data solely. Then, a single and confident classifier is obtained by combining the predictions from multiple experts based on their confidence. Learning of the model is efficient and requires no retraining/reweighting of the source classifiers. We evaluate the proposed approach on two publicly available datasets for multi-class (MultiPIE) and multi-label (DISFA) facial expression classification. To this end, we perform adaptation of two contextual factors: 'where' (view) and 'who' (subject). We show in our experiments that the proposed approach consistently outperforms both source and target classifiers, while using as few as 30 target examples. It also outperforms the state-of-the-art approaches for supervised domain adaptation.