Using Simulated Data to Generate Images of Climate Change
Computer Vision and Pattern Recognition
2020-01-29 v1 Image and Video Processing
Abstract
Generative adversarial networks (GANs) used in domain adaptation tasks have the ability to generate images that are both realistic and personalized, transforming an input image while maintaining its identifiable characteristics. However, they often require a large quantity of training data to produce high-quality images in a robust way, which limits their usability in cases when access to data is limited. In our paper, we explore the potential of using images from a simulated 3D environment to improve a domain adaptation task carried out by the MUNIT architecture, aiming to use the resulting images to raise awareness of the potential future impacts of climate change.
Cite
@article{arxiv.2001.09531,
title = {Using Simulated Data to Generate Images of Climate Change},
author = {Gautier Cosne and Adrien Juraver and Mélisande Teng and Victor Schmidt and Vahe Vardanyan and Alexandra Luccioni and Yoshua Bengio},
journal= {arXiv preprint arXiv:2001.09531},
year = {2020}
}
Comments
Proceeding ML-IRL workshop at ICLR 2020