Image-based model parameter optimization using Model-Assisted Generative Adversarial Networks

TL;DR

This paper introduces a model-assisted GAN that optimizes model parameters to generate fake images matching true images, aiding in reducing bias in image recognition tasks, demonstrated through two case studies.

Contribution

The paper presents a novel use of GANs to directly optimize model parameters for image matching, improving simulation tuning and bias reduction in image analysis.

Findings

Excellent agreement between generated and true parameters in case studies

Model-assisted GAN effectively emulates simulation for fast image generation

Retuning simulation parameters reduces bias in image recognition

Abstract

We propose and demonstrate the use of a model-assisted generative adversarial network (GAN) to produce fake images that accurately match true images through the variation of the parameters of the model that describes the features of the images. The generator learns the model parameter values that produce fake images that best match the true images. Two case studies show excellent agreement between the generated best match parameters and the true parameters. The best match model parameter values can be used to retune the default simulation to minimize any bias when applying image recognition techniques to fake and true images. In the case of a real-world experiment, the true images are experimental data with unknown true model parameter values, and the fake images are produced by a simulation that takes the model parameters as input. The model-assisted GAN uses a convolutional neural network to emulate the simulation for all parameter values that, when trained, can be used as a conditional generator for fast fake-image production.