Abstract
Deep interactive evolution (DeepIE) combines the capacity of interactive evolutionary computation (IEC) to capture a user’s preference with the domain-specific robustness of a trained generative adversarial network (GAN) generator, allowing the user to control the GAN output through evolutionary exploration of the latent space. However, the traditional GAN latent space presents feature entanglement, which limits the practicability of possible applications of DeepIE. In this paper, we implement DeepIE within a style-based generator from a StyleGAN model trained on the WikiArt dataset and propose StyleIE, a variation of DeepIE that takes advantage of the secondary disentangled latent space in the style-based generator. We performed two AB/BA crossover user tests that compared the performance of DeepIE against StyleIE for art generation. Self-rated evaluations of the performance were collected through a questionnaire. Findings from the tests suggest that StyleIE and DeepIE perform equally in tasks with open-ended goals with relaxed constraints, but StyleIE performs better in close-ended and more constrained tasks.
Highlights
In 1987, Richard Dawkins introduced a system of simulated selective breeding of artificial organisms called Biomorph [1], becoming a milestone in the birth of interactive evolutionary computation (IEC) and evolutionary art (EArt) as areas of research [2,3]
This paper explores the intersection of generative adversarial networks (GANs) and interactive evolutionary computation (IEC) within the context of artistic artifact generation and creative expression
One of the strengths of IEC is that it embeds human preferences and intuition into optimization systems, which is very useful in problems with no tractable fitness function, such as in EArt
Summary
In 1987, Richard Dawkins introduced a system of simulated selective breeding of artificial organisms called Biomorph [1], becoming a milestone in the birth of interactive evolutionary computation (IEC) and evolutionary art (EArt) as areas of research [2,3]. IEC can be defined as an evolutionary computation optimization method whose fitness functions are replaced by the subjective evaluation of a human user. It can be difficult or even impossible to design an explicit fitness function This is the case for systems that produce outputs that must be subjectively evaluated, such as art or music. One of the strengths of IEC is that it embeds human preferences and intuition into optimization systems, which is very useful in problems with no tractable fitness function, such as in EArt. Downsides of IEC include the fact that population sizes are limited by the number of individuals the human user could meaningfully evaluate; for this reason, populations in IEC are exponentially smaller than their EC counterparts
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
