# Learn to synthesize and synthesize to learn

## TL;DR

This paper introduces a versatile face image synthesis method that uses a single model to generate multiple realistic faces based on attributes, improving quality and utility for tasks like expression recognition.

## Contribution

A novel attribute-guided face synthesis approach that handles multiple domains with one model, enhancing realism and utility for data augmentation.

## Key findings

- Generated face images are highly photorealistic across datasets.
- The method improves facial expression recognition accuracy.
- Synthetic data augmentation benefits classifier performance.

## Abstract

Attribute guided face image synthesis aims to manipulate attributes on a face image. Most existing methods for image-to-image translation can either perform a fixed translation between any two image domains using a single attribute or require training data with the attributes of interest for each subject. Therefore, these methods could only train one specific model for each pair of image domains, which limits their ability in dealing with more than two domains. Another disadvantage of these methods is that they often suffer from the common problem of mode collapse that degrades the quality of the generated images. To overcome these shortcomings, we propose attribute guided face image generation method using a single model, which is capable to synthesize multiple photo-realistic face images conditioned on the attributes of interest. In addition, we adopt the proposed model to increase the realism of the simulated face images while preserving the face characteristics. Compared to existing models, synthetic face images generated by our method present a good photorealistic quality on several face datasets. Finally, we demonstrate that generated facial images can be used for synthetic data augmentation, and improve the performance of the classifier used for facial expression recognition.