A Sub-Layered Hierarchical Pyramidal Neural Architecture for Facial Expression Recognition
This work addresses the problem of efficient facial expression recognition for applications like robotics where resources are constrained, presenting an incremental improvement in architecture design.
The paper tackles facial expression recognition with limited computational resources and labeled data by introducing a connectivity scheme for pyramidal architectures, achieving good generalization performance and low computational cost comparable to convolutional architectures but with fewer parameters and more robustness for low-resolution faces.
In domains where computational resources and labeled data are limited, such as in robotics, deep networks with millions of weights might not be the optimal solution. In this paper, we introduce a connectivity scheme for pyramidal architectures to increase their capacity for learning features. Experiments on facial expression recognition of unseen people demonstrate that our approach is a potential candidate for applications with restricted resources, due to good generalization performance and low computational cost. We show that our approach generalizes as well as convolutional architectures in this task but uses fewer trainable parameters and is more robust for low-resolution faces.