Title | ||
---|---|---|
An Ensemble With Shared Representations Based On Convolutional Networks For Continually Learning Facial Expressions |
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. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/IROS.2018.8594276 | 2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) |
Field | DocType | ISSN |
Facial recognition system,Social robot,Computer vision,Computer science,Convolution,Emotion recognition,Feature extraction,Redundancy (engineering),Facial expression,Artificial intelligence,Robot,Machine learning | Conference | 2153-0858 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Henrique Siqueira | 1 | 2 | 3.40 |
Pablo V. A. Barros | 2 | 119 | 22.02 |
Sven Magg | 3 | 67 | 13.49 |
Stefan Wermter | 4 | 1100 | 151.62 |