Facial expression recognition using lightweight deep convolutional networks with label distribution learning on action units labels space
Nowadays, the search for ‘lightweight’ solutions that achieve comparable results to those of heavy deep learning models has received increasing attention due to a feasible implementation on mobile devices. One of the areas that might benefit from this approach is the task of Facial Expression Recog...
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Articulo |
| Lenguaje: | Español |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/157870 |
| Aporte de: |
| Sumario: | Nowadays, the search for ‘lightweight’ solutions that achieve comparable results to those of heavy deep learning models has received increasing attention due to a feasible implementation on mobile devices.
One of the areas that might benefit from this approach is the task of Facial Expression Recognition (FER). Considering the fact that datasets usually come with categoric labeling but most emotions occur as combinations, mixtures, or compounds of the basic emotions, we make use of label distribution learning (LDL) as a training strategy. In this article we deal with the FER problem using lightweight neuronal networks and LDL. We further assume that facial images should have similar emotion distributions to their neighbors when the right auxiliary task is considered, like the Action Unit Recognition problem. This neighbors’ distribution information is captured in the loss function to help the LDL training process. Specifically, we conduct an analysis of EfficientFace, a state-of-the-art ligthweight CNN and we analyze the impact of using different approaches to LDL on a variety of in-the-wild datasets: RAF-DB, CAER-S, FER+ and AffectNet. |
|---|