Neural Architecture Search Using Genetic Algorithm for Facial Expression Recognition
This work addresses the tedious and error-prone process of manual architecture design for deep learning researchers in facial expression recognition, representing an incremental improvement using existing NAS methods.
The paper tackled the problem of designing convolutional neural network architectures for facial expression recognition by proposing a genetic algorithm approach, achieving state-of-the-art accuracy on CK+ and FERG datasets and competitive results on JAFFE.
Facial expression is one of the most powerful, natural, and universal signals for human beings to express emotional states and intentions. Thus, it is evident the importance of correct and innovative facial expression recognition (FER) approaches in Artificial Intelligence. The current common practice for FER is to correctly design convolutional neural networks' architectures (CNNs) using human expertise. However, finding a well-performing architecture is often a very tedious and error-prone process for deep learning researchers. Neural architecture search (NAS) is an area of growing interest as demonstrated by the large number of scientific works published in recent years thanks to the impressive results achieved in recent years. We propose a genetic algorithm approach that uses an ingenious encoding-decoding mechanism that allows to automatically evolve CNNs on FER tasks attaining high accuracy classification rates. The experimental results demonstrate that the proposed algorithm achieves the best-known results on the CK+ and FERG datasets as well as competitive results on the JAFFE dataset.