Exploring Low-level and High-level Transfer Learning for Multi-task Facial Recognition with a Semi-supervised Neural Network

Facial recognition tasks like identity, age, gender, and emotion recognition received substantial attention in recent years. Their deployment in robotic platforms became necessary for the characterization of most of the non-verbal Human-Robot Interaction (HRI) scenarios. In this regard, deep convolution neural networks have shown to be effective on processing different facial representations but with a high cost: to achieve maximum generalization, they require an enormous amount of task-specific labeled data. This paper proposes a unified semi- supervised deep neural model to address this problem. Our hybrid model is composed of an unsupervised deep generative adversarial network which learns fundamental characteristics of facial representations, and a set of convolution channels that fine-tunes the high-level facial concepts for the recognition of identity, age group, gender, and facial expressions. Our network employs progressive lateral connections between the convolution channels so that they share the high-abstraction particularities of each of these tasks in order to reduce the necessity of a large amount of strongly labeled training data. We propose a series of experiments to evaluate each individual mechanism of our hybrid model, in particular, the impact of the progressive connections on learning the specific facial recognition tasks and we observe that our model achieves a better performance when compared to task-specific models.

@InProceedings{BFKW19, 
 	 author =  {Barros, Pablo and Fliesswasser, Erik and Kerzel, Matthias and Wermter, Stefan},  
 	 title = {Exploring Low-level and High-level Transfer Learning for Multi-task Facial Recognition with a Semi-supervised Neural Network}, 
 	 booktitle = {2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
 	 editors = {},
 	 number = {},
 	 volume = {},
 	 pages = {1378--1384},
 	 year = {2019},
 	 month = {Nov},
 	 publisher = {},
 	 doi = {10.1109/IROS40897.2019.8968243}, 
 }