Enhancing Authorship Attribution with Synthetic Paintings

2026-03-04

AI Summary

This work addresses the performance bottleneck in artistic authorship attribution caused by the scarcity of authentic training data. To overcome this limitation, the authors propose an innovative approach that leverages DreamBooth to fine-tune Stable Diffusion for generating synthetic paintings in the distinctive styles of specific artists. These synthetic images are then combined with limited real-world data to construct a hybrid training set for a discriminative classification model. This study represents the first effective integration of generative synthetic imagery into the task of artwork authorship attribution, significantly enhancing model performance under data-scarce conditions. Experimental results demonstrate that models trained on the augmented dataset consistently outperform baseline methods that rely solely on real data, achieving higher ROC-AUC scores and accuracy, thereby validating the efficacy and generalizability of the proposed strategy.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Attributing authorship to paintings is a historically complex task, and one of its main challenges is the limited availability of real artworks for training computational models. This study investigates whether synthetic images, generated through DreamBooth fine-tuning of Stable Diffusion, can improve the performance of classification models in this context. We propose a hybrid approach that combines real and synthetic data to enhance model accuracy and generalization across similar artistic styles. Experimental results show that adding synthetic images leads to higher ROC-AUC and accuracy compared to using only real paintings. By integrating generative and discriminative methods, this work contributes to the development of computer vision techniques for artwork authentication in data-scarce scenarios.

Problem

• authorship attribution
• paintings
• data scarcity
• artwork authentication
• computational models

Innovation

• synthetic paintings
• authorship attribution
• DreamBooth
• Stable Diffusion
• data augmentation