Quantifying Confounding Bias in Generative Art: A Case Study

• URL: http://arxiv.org/abs/2102.11957v1
• Date: Tue, 23 Feb 2021 21:59:30 GMT
• Title: Quantifying Confounding Bias in Generative Art: A Case Study
• Authors: Ramya Srinivasan, Kanji Uchino
• Abstract summary: We propose a simple metric to quantify confounding bias due to the lack of modeling the influence of art movements in learning artists' styles. The proposed metric is more effective than state-of-the-art outlier detection method in understanding the influence of art movements in artworks.
• Score: 3.198144010381572
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In recent years, AI generated art has become very popular. From generating art works in the style of famous artists like Paul Cezanne and Claude Monet to simulating styles of art movements like Ukiyo-e, a variety of creative applications have been explored using AI. Looking from an art historical perspective, these applications raise some ethical questions. Can AI model artists' styles without stereotyping them? Does AI do justice to the socio-cultural nuances of art movements? In this work, we take a first step towards analyzing these issues. Leveraging directed acyclic graphs to represent potential process of art creation, we propose a simple metric to quantify confounding bias due to the lack of modeling the influence of art movements in learning artists' styles. As a case study, we consider the popular cycleGAN model and analyze confounding bias across various genres. The proposed metric is more effective than state-of-the-art outlier detection method in understanding the influence of art movements in artworks. We hope our work will elucidate important shortcomings of computationally modeling artists' styles and trigger discussions related to accountability of AI generated art.

Related papers

• GalleryGPT: Analyzing Paintings with Large Multimodal Models [64.98398357569765]
  Artwork analysis is important and fundamental skill for art appreciation, which could enrich personal aesthetic sensibility and facilitate the critical thinking ability. Previous works for automatically analyzing artworks mainly focus on classification, retrieval, and other simple tasks, which is far from the goal of AI. We introduce a superior large multimodal model for painting analysis composing, dubbed GalleryGPT, which is slightly modified and fine-tuned based on LLaVA architecture.
  arXiv  Detail & Related papers  (2024-08-01T11:52:56Z)
• Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models [47.19481598385283]
  ArtSavant is a tool to determine the unique style of an artist by comparing it to a reference dataset of works from WikiArt. We then perform a large-scale empirical study to provide quantitative insight on the prevalence of artistic style copying across 3 popular text-to-image generative models.
  arXiv  Detail & Related papers  (2024-04-11T17:59:43Z)
• AI Art Neural Constellation: Revealing the Collective and Contrastive State of AI-Generated and Human Art [36.21731898719347]
  We conduct a comprehensive analysis to position AI-generated art within the context of human art heritage. Our comparative analysis is based on an extensive dataset, dubbed ArtConstellation'' Key finding is that AI-generated artworks are visually related to the principle concepts for modern period art made in 1800-2000.
  arXiv  Detail & Related papers  (2024-02-04T11:49:51Z)
• Foregrounding Artist Opinions: A Survey Study on Transparency, Ownership, and Fairness in AI Generative Art [0.0]
  Generative AI tools are used to create art-like outputs and sometimes aid in the creative process. We surveyed 459 artists to investigate tension between artists' opinions on Generative AI art's potential utility and harm.
  arXiv  Detail & Related papers  (2024-01-27T20:22:46Z)
• Impressions: Understanding Visual Semiotics and Aesthetic Impact [66.40617566253404]
  We present Impressions, a novel dataset through which to investigate the semiotics of images. We show that existing multimodal image captioning and conditional generation models struggle to simulate plausible human responses to images. This dataset significantly improves their ability to model impressions and aesthetic evaluations of images through fine-tuning and few-shot adaptation.
  arXiv  Detail & Related papers  (2023-10-27T04:30:18Z)
• Artificial Intelligence and Aesthetic Judgment [29.71278672770529]
  Generative AIs produce creative outputs in the style of human expression. We argue that encounters with the outputs of modern generative AI models are mediated by the same kinds of aesthetic judgments.
  arXiv  Detail & Related papers  (2023-08-21T17:40:54Z)
• Learning to Evaluate the Artness of AI-generated Images [64.48229009396186]
  ArtScore is a metric designed to evaluate the degree to which an image resembles authentic artworks by artists. We employ pre-trained models for photo and artwork generation, resulting in a series of mixed models. This dataset is then employed to train a neural network that learns to estimate quantized artness levels of arbitrary images.
  arXiv  Detail & Related papers  (2023-05-08T17:58:27Z)
• Inversion-Based Style Transfer with Diffusion Models [78.93863016223858]
  Previous arbitrary example-guided artistic image generation methods often fail to control shape changes or convey elements. We propose an inversion-based style transfer method (InST), which can efficiently and accurately learn the key information of an image.
  arXiv  Detail & Related papers  (2022-11-23T18:44:25Z)
• Can There be Art Without an Artist? [1.2691047660244335]
  Generative AI based art has proliferated in the past year. In this paper, we explore how Generative Models have impacted artistry. We posit that if deployed responsibly, AI generative models have the possibility of being a positive, new modality in art.
  arXiv  Detail & Related papers  (2022-09-16T01:23:19Z)
• Art Creation with Multi-Conditional StyleGANs [81.72047414190482]
  A human artist needs a combination of unique skills, understanding, and genuine intention to create artworks that evoke deep feelings and emotions. We introduce a multi-conditional Generative Adversarial Network (GAN) approach trained on large amounts of human paintings to synthesize realistic-looking paintings that emulate human art.
  arXiv  Detail & Related papers  (2022-02-23T20:45:41Z)
• Biases in Generative Art -- A Causal Look from the Lens of Art History [3.198144010381572]
  We investigate biases in the generative art AI pipeline from those that can originate due to improper problem formulation to those related to algorithm design. We highlight how current methods fall short in modeling the process of art creation and thus contribute to various types of biases.
  arXiv  Detail & Related papers  (2020-10-26T00:49:09Z)

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.