Synthetic Data Augmentation for Multi-Task Chinese Porcelain Classification: A Stable Diffusion Approach

TL;DR

This paper explores using Stable Diffusion with LoRA to generate synthetic images for augmenting limited datasets in Chinese porcelain classification, improving model performance in certain tasks.

Contribution

It demonstrates the effectiveness of synthetic data augmentation via Stable Diffusion for multi-task archaeological artifact classification, providing practical guidelines.

Findings

Type classification improved by 5.5% F1-macro with synthetic data.

Modest gains (3-4%) in dynasty and kiln tasks.

Synthetic augmentation effectiveness varies with task relevance.

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.