neural networks research group
areas
people
projects
demos
publications
software/data
Evolving GAN Formulations for Higher Quality Image Synthesis (2023)
Santiago Gonzalez
, Mohak Kant, and
Risto Miikkulainen
Generative Adversarial Networks (GANs) have extended deep learning to complex generation and translation tasks across different data modalities. However, GANs are notoriously difficult to train: Mode collapse and other instabilities in the training process often degrade the quality of the generated results, such as images. This paper presents a new technique called TaylorGAN for improving GANs by discovering customized loss functions for each of its two networks. The loss functions are parameterized as Taylor expansions and optimized through multiobjective evolution. On an image-to-image translation benchmark task, this approach qualitatively improves generated image quality and quantitatively improves two independent GAN performance metrics. It therefore forms a promising approach for applying GANs to more challenging tasks in the future.
View:
PDF
Citation:
To Appear In R. Kozma, C. Alippi, Y. Choe, and F. C. Morabito, editors,
Artificial Intelligence in the Age of Neural Networks and Brain Computing (second edition)
, New York, 2023. Elsevier. Also arXiv:2102.08578.
Bibtex:
@incollection{gonzalez:chapter23, title={Evolving GAN Formulations for Higher Quality Image Synthesis}, author={Santiago Gonzalez and Mohak Kant and Risto Miikkulainen}, booktitle={Artificial Intelligence in the Age of Neural Networks and Brain Computing (second edition)}, month={ }, editor={R. Kozma and C. Alippi and Y. Choe and F. C. Morabito}, address={New York}, publisher={Elsevier}, note={Also arXiv:2102.08578}, url="http://nn.cs.utexas.edu/?gonzalez:chapter23", year={2023} }
People
Santiago Gonzalez
Ph.D. Alumni
slgonzalez [at] utexas edu
Risto Miikkulainen
Faculty
risto [at] cs utexas edu
Areas of Interest
Evolutionary Computation
Neuroevolution