An Ensemble with Shared Representations Based on Convolutional Networks for Continually Learning Facial Expressions
This work addresses the challenge of efficient emotion recognition for social robots, though it appears incremental in improving existing ensemble methods.
The paper tackled the problem of reducing redundancy in ensemble-based systems for continual learning of facial expressions in social robots, achieving a significant drop in low-level feature processing redundancy.
Social robots able to continually learn facial expressions could progressively improve their emotion recognition capability towards people interacting with them. Semi-supervised learning through ensemble predictions is an efficient strategy to leverage the high exposure of unlabelled facial expressions during human-robot interactions. Traditional ensemble-based systems, however, are composed of several independent classifiers leading to a high degree of redundancy, and unnecessary allocation of computational resources. In this paper, we proposed an ensemble based on convolutional networks where the early layers are strong low-level feature extractors, and their representations shared with an ensemble of convolutional branches. This results in a significant drop in redundancy of low-level features processing. Training in a semi-supervised setting, we show that our approach is able to continually learn facial expressions through ensemble predictions using unlabelled samples from different data distributions.