CADA-GAN: Context-Aware GAN with Data Augmentation

TL;DR

CADA-GAN is a novel context-aware GAN that enhances child face generation by optimizing feature extraction and robustness through data augmentation, based on StyleGAN2-Ada.

Contribution

It introduces a context-aware architecture with data augmentation for improved feature extraction and robustness in child face generation.

Findings

Lowest MSE loss on latent features

Generated images show increased robustness

Effective segmentation and augmentation of parent images

Abstract

Current child face generators are restricted by the limited size of the available datasets. In addition, feature selection can prove to be a significant challenge, especially due to the large amount of features that need to be trained for. To manage these problems, we proposed CADA-GAN, a \textbf{C}ontext-\textbf{A}ware GAN that allows optimal feature extraction, with added robustness from additional \textbf{D}ata \textbf{A}ugmentation. CADA-GAN is adapted from the popular StyleGAN2-Ada model, with attention on augmentation and segmentation of the parent images. The model has the lowest \textit{Mean Squared Error Loss} (MSEloss) on latent feature representations and the generated child image is robust compared with the one that generated from baseline models.