Automated Goldsmith's Mark Retrieval in Silverware

2026-09-17

AI Summary

为解决金银器上金匠标记的手动比对问题，提出了一种结合标记定位与度量学习微调的AI辅助检索方法，使用了三种骨干架构，并取得了显著效果。

Abstract

For art historians, goldsmith marks play a critical role in the identification and dating of artifacts. In practice, experts must manually compare a query mark against hundreds of documented examples, a process that is both tedious and highly dependent on specialist knowledge. To address this, we present an AI-assisted retrieval pipeline that combines mark localization with metric-learning fine-tuning across three backbone architectures: an ImageNet-pretrained ResNet-50, a supervised ViT-S/16, and a self-supervised DINOv2 ViT-S/14. We conduct a systematic evaluation of cropping strategies, where we measure the impact of no cropping, manual ground-truth cropping, and learned detection-based cropping, and assess their interaction with each backbone. Our strongest configuration, DINOv2 ViT-S/14 with manual crop and metric-learning fine-tuning, achieves an mAP of 62.63% and a Top-1 accuracy of 73.74%. Our experiments show that self-supervised pretraining and mark localization are the two most impactful factors, with learned cropping recovering the majority of the gain from manual cropping without requiring ground-truth annotations at inference time. To enable reproducibility and adoption in the digital humanities, we release our manually annotated dataset and codebase, and deploy the system via a public web interface.

Problem

• goldsmith marks
• artifacts identification
• dating artifacts
• manual comparison
• specialist knowledge

Innovation

• metric-learning fine-tuning
• self-supervised pretraining
• mark localization
• learned cropping