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

<p> 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. </p>

@InProceedings{SBMW18, 
 	 author =  {Siqueira, Henrique and Barros, Pablo and Magg, Sven and Wermter, Stefan},  
 	 title = {An Ensemble with Shared Representations Based on Convolutional Networks for Continually Learning Facial Expressions}, 
 	 booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
 	 editors = {},
 	 number = {},
 	 volume = {},
 	 pages = {1563--1568},
 	 year = {2018},
 	 month = {Oct},
 	 publisher = {},
 	 doi = {10.1109/IROS.2018.8594276}, 
 }