Quality-diversity for aesthetic evolution

• URL: http://arxiv.org/abs/2202.01961v1
• Date: Fri, 4 Feb 2022 04:11:21 GMT
• Title: Quality-diversity for aesthetic evolution
• Authors: Jon McCormack and Camilo Cruz Gambardella
• Abstract summary: We apply quality-diversity search methods to explore a creative generative system. To compute diversity we use a convolutional neural network to discriminate features that are dimensionally reduced into two dimensions. We show that the quality-diversity search is able to find multiple phenotypes of high aesthetic value.
• Score: 5.837881923712394
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Many creative generative design spaces contain multiple regions with individuals of high aesthetic value. Yet traditional evolutionary computing methods typically focus on optimisation, searching for the fittest individual in a population. In this paper we apply quality-diversity search methods to explore a creative generative system (an agent-based line drawing model). We perform a random sampling of genotype space and use individual artist-assigned evaluations of aesthetic quality to formulate a computable fitness measure specific to the artist and this system. To compute diversity we use a convolutional neural network to discriminate features that are dimensionally reduced into two dimensions. We show that the quality-diversity search is able to find multiple phenotypes of high aesthetic value. These phenotypes show greater diversity and quality than those the artist was able to find using manual search methods.

Related papers

• GRADE: Quantifying Sample Diversity in Text-to-Image Models [66.12068246962762]
  We propose GRADE: Granular Attribute Diversity Evaluation, an automatic method for quantifying sample diversity. We measure the overall diversity of 12 T2I models using 400 concept-attribute pairs, revealing that all models display limited variation. Our work proposes a modern, semantically-driven approach to measure sample diversity and highlights the stunning homogeneity in outputs by T2I models.
  arXiv  Detail & Related papers  (2024-10-29T23:10:28Z)
• Generalized People Diversity: Learning a Human Perception-Aligned Diversity Representation for People Images [11.038712922077458]
  We introduce a diverse people image ranking method which more flexibly aligns with human notions of people diversity. The Perception-Aligned Text-derived Human representation Space (PATHS) aims to capture all or many relevant features of people-related diversity.
  arXiv  Detail & Related papers  (2024-01-25T17:19:22Z)
• Diverse Diffusion: Enhancing Image Diversity in Text-to-Image Generation [0.0]
  We introduce Diverse Diffusion, a method for boosting image diversity beyond gender and ethnicity. Our approach contributes to the creation of more inclusive and representative AI-generated art.
  arXiv  Detail & Related papers  (2023-10-19T08:48:23Z)
• Creative Discovery using QD Search [4.941630596191806]
  This paper introduces a method that combines evolutionary optimisation with AI-based image classification to perform quality-diversity search. We tested our method on a generative system that produces abstract drawings.
  arXiv  Detail & Related papers  (2023-05-08T05:11:02Z)
• Few-Shot Meta Learning for Recognizing Facial Phenotypes of Genetic Disorders [55.41644538483948]
  Automated classification and similarity retrieval aid physicians in decision-making to diagnose possible genetic conditions as early as possible. Previous work has addressed the problem as a classification problem and used deep learning methods. In this study, we used a facial recognition model trained on a large corpus of healthy individuals as a pre-task and transferred it to facial phenotype recognition.
  arXiv  Detail & Related papers  (2022-10-23T11:52:57Z)
• What can phylogenetic metrics tell us about useful diversity in evolutionary algorithms? [62.997667081978825]
  Phylogenetic diversity metrics are a class of metrics popularly used in biology. We find that, in most cases, phylogenetic metrics behave meaningfully differently from other diversity metrics.
  arXiv  Detail & Related papers  (2021-08-28T06:49:14Z)
• Expressivity of Parameterized and Data-driven Representations in Quality Diversity Search [111.06379262544911]
  We compare the output diversity of a quality diversity evolutionary search performed in two different search spaces. A learned model is better at interpolating between known data points than at extrapolating or expanding towards unseen examples.
  arXiv  Detail & Related papers  (2021-05-10T10:27:43Z)
• A Novel Bio-Inspired Texture Descriptor based on Biodiversity and Taxonomic Measures [81.08571247838206]
  We propose a novel approach capable of quantifying a complex system of diverse patterns through species diversity and richness and taxonomic distinctiveness. The proposed approach considers each image channel as a species ecosystem and computes species diversity and richness measures as well as taxonomic measures to describe the texture.
  arXiv  Detail & Related papers  (2021-02-13T20:14:14Z)
• Random Network Distillation as a Diversity Metric for Both Image and Text Generation [62.13444904851029]
  We develop a new diversity metric that can be applied to data, both synthetic and natural, of any type. We validate and deploy this metric on both images and text.
  arXiv  Detail & Related papers  (2020-10-13T22:03:52Z)
• Deep Learning of Individual Aesthetics [5.837881923712394]
  We investigate the relationship between image measures, such as complexity, and human aesthetic evaluation. We use dimension reduction methods to visualise both genotype and phenotype space in order to support the exploration of new territory in a generative system. We integrate this classification and discovery system into a software tool for evolving complex generative art and design.
  arXiv  Detail & Related papers  (2020-09-24T03:04:28Z)
• Understanding Aesthetic Evaluation using Deep Learning [5.837881923712394]
  In this paper we look at how recent advances in deep learning can assist in automating personal aesthetic judgement. We use dimensionality reduction methods to visualise both genotype and phenotype space in order to support the exploration of new territory in any generative system. Convolutional Neural Networks trained on the user's prior aesthetic evaluations are used to suggest new possibilities similar or between known high quality genotype-phenotype mappings.
  arXiv  Detail & Related papers  (2020-04-15T04:18:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.