An Ensemble with Shared Representations Based on Convolutional Networks for Continually Learning Facial Expressions

TL;DR

This paper introduces a convolutional network ensemble with shared low-level features for continual learning of facial expressions, reducing redundancy and leveraging semi-supervised learning to improve emotion recognition over time.

Contribution

It proposes a shared representation ensemble architecture that decreases redundancy and enables continual semi-supervised learning of facial expressions.

Findings

Reduces computational redundancy in ensemble models.

Enables continual learning from unlabelled data.

Improves emotion recognition accuracy over time.

Abstract

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.