Semantic Data Augmentation for Long-tailed Facial Expression Recognition

TL;DR

This paper introduces a semantic augmentation technique using VAE-GAN to generate balanced facial expression data, improving recognition in long-tailed datasets and potentially benefiting various data-intensive applications.

Contribution

A novel semantic augmentation method leveraging VAE-GAN for balancing long-tailed facial expression datasets, enhancing recognition performance.

Findings

Improved recognition accuracy on RAF-DB dataset.

Effective balancing of long-tailed data distribution.

Applicable to diverse data-hungry scenarios.

Abstract

Facial Expression Recognition has a wide application prospect in social robotics, health care, driver fatigue monitoring, and many other practical scenarios. Automatic recognition of facial expressions has been extensively studied by the Computer Vision research society. But Facial Expression Recognition in real-world is still a challenging task, partially due to the long-tailed distribution of the dataset. Many recent studies use data augmentation for Long-Tailed Recognition tasks. In this paper, we propose a novel semantic augmentation method. By introducing randomness into the encoding of the source data in the latent space of VAE-GAN, new samples are generated. Then, for facial expression recognition in RAF-DB dataset, we use our augmentation method to balance the long-tailed distribution. Our method can be used in not only FER tasks, but also more diverse data-hungry scenarios.