Additional work might include training on paintings of landscapes instead of photos for the Transfer Learning. This may help the GAN pick up on a painterly look to apply to abstract paintings.
I would like to thank Jennifer Lim, Oliver Strimpel, Mahsa Mesgaran, and
Vahid Khorasani for their help and feedback on this project.
The 850 abstract paintings I collected can be found on Kaggle here. All source code for this project is available on GitHub. The sources are released under the CC BY-NC-SA license.
[1] Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., and Aila., T., “Training Generative Adversarial Networks with Limited Data.”, October 7, 2020, https://arxiv.org/pdf/2006.06676.pdf
[2] Eiter, T. and Mannila, H., “Computing the Discrete Fréchet Distance”, Christian Doppler Labor für Expertensyteme, April 25, 1994, http://www.kr.tuwien.ac.at/staff/eiter/et-archive/cdtr9464.pdf
[3] Bozinovskim S., and Fulgosi, A., “The influence of pattern similarity and transfer learning upon training of a base perceptron B2.” Proceedings of Symposium Informatica, 3–121–5, 1976
[4] Bozinovski, S., “Reminder of the first paper on transfer learning in neural networks, 1976”. Informatica 44: 291–302, 2020, http://www.informatica.si/index.php/informatica/article/view/2828