Evolutionary image composition using feature covariance matrices

Proceedings of the Genetic and Evolutionary Computation Conference

Gao

Wagner

et al. 2019

Self Cite

Evolutionary diversity optimization aims to compute a diverse set of solutions where all solutions meet a given quality criterion. With this paper, we bridge the areas of evolutionary diversity optimization and evolutionary multi-objective optimization. We show how popular indicators frequently used in the area of multi-objective optimization can be used for evolutionary diversity optimization. Our experimental investigations for evolving diverse sets of TSP instances and images according to various features show that two of the most prominent multi-objective indicators, namely the hypervolume indicator and the inverted generational distance, provide excellent results in terms of visualization and various diversity indicators.

“…Random walk lengths are increased in the case of a successful mutation and decreased in the case of unsuccessful ones. For details, we refer the reader to [17,18].…”

Section: Imagesmentioning

confidence: 99%

Evolutionary diversity optimization using multi-objective indicators

Proceedings of the Genetic and Evolutionary Computation Conference

Gao

Wagner

et al. 2019

Self Cite

“…Our new mutation operator enables us to construct diverse sets of images for all three algorithms (including (µ + λ)-EA C investigated in [1]) within just 2000 generations. The random walk in this paper differs from the one for image composition given in [20] by changing the RGB values by an offset vector o ∈ [−r, r] 3 chosen in each mutation step uniformly at random. The mutation operator is shown in the Algorithm 2.…”

Section: Self Adaptive Offset Random Walk Mutationmentioning

confidence: 99%

Discrepancy-based evolutionary diversity optimization

Proceedings of the Genetic and Evolutionary Computation Conference

Gao

Doerr

et al. 2018

Self Cite

Diversity plays a crucial role in evolutionary computation. While diversity has been mainly used to prevent the population of an evolutionary algorithm from premature convergence, the use of evolutionary algorithms to obtain a diverse set of solutions has gained increasing attention in recent years. Diversity optimization in terms of features on the underlying problem allows to obtain a better understanding of possible solutions to the problem at hand and can be used for algorithm selection when dealing with combinatorial optimization problems such as the Traveling Salesperson Problem. We explore the use of the star-discrepancy measure to guide the diversity optimization process of an evolutionary algorithm.In our experimental investigations, we consider our discrepancy-based diversity optimization approaches for evolving diverse sets of images as well as instances of the Traveling Salesperson problem where a local search is not able to find near optimal solutions. Our experimental investigations comparing three diversity optimization approaches show that a discrepancy-based diversity optimization approach using a tie-breaking rule based on weighted differences to surrounding feature points provides the best results in terms of the star discrepancy measure.

“…Aesthetic feature measures have been often applied to the creation of new artistic images using evolutionary search [3,4,14,16]. There has also been significant work in the evolution of existing images [20,22]. This work differs from previous work in the use of a GAN as a mapper from the latent search vector to the images space and the use of the discriminator network and feature metrics to constrain these images, the space of a generator network as a given image source and use the discriminator and feature metrics to constrain these images.…”

Section: Related Workmentioning

confidence: 99%

Evolution of Images with Diversity and Constraints Using a Generative Adversarial Network

Neural Information Processing

Pyromallis

Alexander

2018

Self Cite

Evolutionary search has been extensively used to generate artistic images. Raw images have high dimensionality which makes a direct search for an image challenging. In previous work this problem has been addressed by using compact symbolic encodings or by constraining images with priors. Recent developments in deep learning have enabled a generation of compelling artistic images using generative networks that encode images with lower-dimensional latent spaces. To date this work has focused on the generation of images concordant with one or more classes and transfer of artistic styles. There is currently no work which uses search in this latent space to generate images scoring high or low aesthetic measures. In this paper we use evolutionary methods to search for images in two datasets, faces and butterflies, and demonstrate the effect of optimising aesthetic feature scores in one or two dimensions. The work gives a preliminary indication of which feature measures promote the most interesting images and how some of these measures interact.