Gaussian Process Domain Experts for Model Adaptation in Facial Behavior Analysis

TL;DR

This paper introduces a probabilistic Gaussian process-based method for supervised domain adaptation in facial expression classification, effectively combining source and target data to improve accuracy with minimal target examples.

Contribution

The paper proposes a novel Gaussian process framework for domain adaptation that learns from both source and target data without retraining source classifiers, enhancing facial behavior analysis.

Findings

Outperforms state-of-the-art domain adaptation methods.

Achieves high accuracy with as few as 30 target examples.

Effective for both multi-class and multi-label facial expression tasks.

Abstract

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.