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.
@article{arxiv.2603.04343,
title = {Enhancing Authorship Attribution with Synthetic Paintings},
author = {Clarissa Loures and Caio Hosken and Luan Oliveira and Gianlucca Zuin and Adriano Veloso},
journal= {arXiv preprint arXiv:2603.04343},
year = {2026}
}
Comments
Accepted for publication at the 24th IEEE International Conference on Machine Learning and Applications (ICMLA 2025)