Abstract
The scarcity of training data presents a fundamental challenge in applying deep learning to archaeological artifact classification, particularly for the rare types of Chinese porcelain. This study investigates whether synthetic images generated through Stable Diffusion with Low-Rank Adaptation (LoRA) can effectively augment limited real datasets for multi-task CNN-based porcelain classification. Using MobileNetV3 with transfer learning, we conducted controlled experiments comparing models trained on pure real data against those trained on mixed real-synthetic datasets (95:5 and 90:10 ratios) across four classification tasks: dynasty, glaze, kiln and type identification. Results demonstrate task-specific benefits: type classification showed the most substantial improvement (5.5\% F1-macro increase with 90:10 ratio), while dynasty and kiln tasks exhibited modest gains (3-4\%), suggesting that synthetic augmentation effectiveness depends on the alignment between generated features and task-relevant visual signatures. Our work contributes practical guidelines for deploying generative AI in archaeological research, demonstrating both the potential and limitations of synthetic data when archaeological authenticity must be balanced with data diversity.
Abstract (translated)
训练数据的稀缺性是将深度学习应用于考古文物分类，特别是对于稀有类型的中国瓷器时面临的基本挑战。本研究探讨了通过稳定扩散与低秩适应（LoRA）生成的合成图像是否可以有效扩充有限的真实数据集，以用于基于多任务CNN的瓷器分类。我们使用带有迁移学习的MobileNetV3进行了对比实验，将仅用真实数据训练的模型与混合有真实和合成数据集（95:5 和 90:10 比例）的模型在四个分类任务上进行比较：朝代、釉色、窑口及类型识别。结果显示特定任务的具体优势：类型分类表现出最显著的改进（使用90:10比例时，F1-macro分数提升了5.5%），而朝代和窑口任务则显示出较小的增长（3-4%）。这表明合成数据增强的效果取决于生成特征与任务相关的视觉签名之间的对齐程度。我们的研究为在考古学中部署生成式AI提供了实用指导，并展示了当需要平衡文物真实性与数据多样性时，合成数据的潜力及其局限性。
URL
https://arxiv.org/abs/2601.14791
