Synthetic Data Augmentation for Multi-Task Chinese Porcelain Classification: A Stable Diffusion Approach
This addresses data scarcity in archaeological artifact classification, offering practical guidelines for generative AI use, though it is incremental as it applies an existing method to a new domain.
The study tackled the scarcity of training data for Chinese porcelain classification by using Stable Diffusion with LoRA to generate synthetic images for augmentation, resulting in task-specific improvements such as a 5.5% F1-macro increase for type classification with a 90:10 real-synthetic ratio.
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.