EvoGAN: An Evolutionary Computation Assisted GAN

TL;DR

EvoGAN introduces an evolutionary algorithm to guide GANs in synthesizing diverse and accurate compound facial expressions, overcoming gradient-based limitations and enabling more complex expression generation.

Contribution

The paper presents a novel EA-assisted GAN framework that generates complex compound facial expressions with high accuracy, expanding the capabilities of traditional gradient-based methods.

Findings

Successfully synthesizes various compound expressions

Demonstrates high accuracy in expression recognition

Shows potential for diverse facial image generation

Abstract

The image synthesis technique is relatively well established which can generate facial images that are indistinguishable even by human beings. However, all of these approaches uses gradients to condition the output, resulting in the outputting the same image with the same input. Also, they can only generate images with basic expression or mimic an expression instead of generating compound expression. In real life, however, human expressions are of great diversity and complexity. In this paper, we propose an evolutionary algorithm (EA) assisted GAN, named EvoGAN, to generate various compound expressions with any accurate target compound expression. EvoGAN uses an EA to search target results in the data distribution learned by GAN. Specifically, we use the Facial Action Coding System (FACS) as the encoding of an EA and use a pre-trained GAN to generate human facial images, and then use a pre-trained classifier to recognize the expression composition of the synthesized images as the fitness function to guide the search of the EA. Combined random searching algorithm, various images with the target expression can be easily sythesized. Quantitative and Qualitative results are presented on several compound expressions, and the experimental results demonstrate the feasibility and the potential of EvoGAN.