银器中金匠印记的自动化检索
Automated Goldsmith's Mark Retrieval in Silverware
浏览论文内容
中文总结 AI 辅助
针对银器金匠印记检索依赖人工且繁琐的问题，提出结合印记定位与度量学习微调的AI检索流程，其中DINOv2 ViT-S/14配置最优，mAP达62.63%，并公开数据集与代码。
中文摘要 AI 辅助
对于艺术史学家而言，金匠印记在文物的鉴定和断代中起着关键作用。在实践中，专家必须将查询印记与数百个有记录的示例进行手动比对，这一过程既繁琐又高度依赖专业知识。为解决这一问题，我们提出了一种AI辅助检索流程，该流程结合了印记定位与度量学习微调，并采用了三种骨干架构：ImageNet预训练的ResNet-50、有监督的ViT-S/16以及自监督的DINOv2 ViT-S/14。我们对裁剪策略进行了系统性评估，测量了无裁剪、手动真值裁剪和基于学习的检测裁剪的影响，并评估了它们与每种骨干架构的交互作用。我们最强的配置，即采用手动裁剪和度量学习微调的DINOv2 ViT-S/14，实现了62.63%的mAP和73.74%的Top-1准确率。实验表明，自监督预训练和印记定位是两个影响最大的因素，而学习裁剪在推理时无需真值标注即可恢复手动裁剪的大部分增益。为了促进数字人文学科中的可复现性和采用，我们发布了手动标注的数据集和代码库，并通过公共网络界面部署了该系统。
英文摘要
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.
发表机构
- Pattern Recognition Lab, FAU Erlangen-Nürnberg（埃尔朗根-纽伦堡大学模式识别实验室）
- Germanisches Nationalmuseum Nürnberg（纽伦堡日耳曼国家博物馆）
机构由 AI 辅助整理，请以论文原文为准。
