用合成画作提升画作风格归属识别准确率
Enhancing Authorship Attribution with Synthetic Paintings
- 用DreamBooth微调Stable Diffusion生成合成画作
- 混合真实与合成数据使模型AUC和准确率提升
- 适合数据稀缺场景下的艺术作品鉴真研究
判断画作风格归属是历史难题，主要挑战在于真实艺术品数据不足。本研究探讨通过DreamBooth微调Stable Diffusion生成的合成图像，能否提升分类模型在该任务中的表现。提出一种结合真实与合成数据的混合方法，以增强模型在相似艺术风格间的泛化能力。实验结果表明，加入合成图像后，模型在ROC-AUC和准确率上均优于仅使用真实画作的情况。通过融合生成与判别方法，本工作推动了数据稀缺场景下艺术作品认证的计算机视觉技术发展。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。