Diversity and stylization of the contemporary user-generated visual arts in the complexity-entropy plane

2024-08-19

arXiv.org

AI Summary

This study investigates the evolutionary mechanisms and drivers of diversity in user-generated visual art styles from 2010–2020. Method: Leveraging 149,000 artworks from DeviantArt and Behance, we introduce the Complexity–Entropy (C–H) plane—a novel paradigm for quantifying local image structure—and integrate physics-inspired C–H analysis, multi-layer deep feature extraction (ResNet/ViT), and rigorous statistical significance testing. Contribution/Results: We empirically identify an emergent-art-style region on the C–H plane characterized by both novelty and high representational diversity—the first such quantitative marker of nascent artistic movements. Results demonstrate strong temporal correlations between C–H metrics and multi-level visual feature divergence, enabling the first scalable, quantitative macro-model of large-scale collective visual creativity evolution. This work establishes an interdisciplinary theoretical framework and empirically grounded criteria for modeling artistic style evolution.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Humans and AI: Crowd Sourcing and Human Computation

Application Category

• Web Mining and Content Analysis: Models for Web evolution
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

Abstract

The advent of computational and numerical methods in recent times has provided new avenues for analyzing art historiographical narratives and tracing the evolution of art styles therein. Here, we investigate an evolutionary process underpinning the emergence and stylization of contemporary user-generated visual art styles using the complexity-entropy (C-H) plane, which quantifies local structures in paintings. Informatizing 149,780 images curated in DeviantArt and Behance platforms from 2010 to 2020, we analyze the relationship between local information of the C-H space and multi-level image features generated by a deep neural network and a feature extraction algorithm. The results reveal significant statistical relationships between the C-H information of visual artistic styles and the dissimilarities of the multi-level image features over time within groups of artworks. By disclosing a particular C-H region where the diversity of image representations is noticeably manifested, our analyses reveal an empirical condition of emerging styles that are both novel in the C-H plane and characterized by greater stylistic diversity. Our research shows that visual art analyses combined with physics-inspired methodologies and machine learning, can provide macroscopic insights into quantitatively mapping relevant characteristics of an evolutionary process underpinning the creative stylization of uncharted visual arts of given groups and time.

Problem

• Analyzing diversity and stylization of user-generated visual arts
• Quantifying art styles using complexity-entropy plane and machine learning
• Mapping evolutionary process of emerging visual art styles

Innovation

• Using complexity-entropy plane for art analysis
• Combining deep neural networks with feature extraction
• Physics-inspired methods for mapping art evolution