用少量样本实现古乐谱符号分类，提升文化遗产数字化效率。
Low-Data Classification of Historical Music Manuscripts: A Few-Shot Learning Approach
- 基于自监督学习构建特征提取器，无需大量标注数据
- 在少样本条件下达到87.66%分类准确率
- 适合古籍数字化与历史音乐遗产保护研究者
本文探索技术与文化保存的交叉领域，提出一种用于历史乐谱中音乐符号分类的自监督学习框架。光学乐谱识别（OMR）在音乐遗产数字化与保存中至关重要，但历史文献常缺乏传统方法所需的标注数据。我们通过在无标签数据上训练神经网络特征提取器，实现仅用少量样本即可有效分类。关键贡献包括优化用于自监督卷积神经网络的裁剪预处理，并评估支持向量机、多层感知机及原型网络等分类方法。实验结果显示分类准确率达87.66%，展示了人工智能驱动方法在先进数字存档技术中保障历史音乐传承的潜力。
原文摘要 · Abstract (English)
In this paper, we explore the intersection of technology and cultural preservation by developing a self-supervised learning framework for the classification of musical symbols in historical manuscripts. Optical Music Recognition (OMR) plays a vital role in digitising and preserving musical heritage, but historical documents often lack the labelled data required by traditional methods. We overcome this challenge by training a neural-based feature extractor on unlabelled data, enabling effective classification with minimal samples. Key contributions include optimising crop preprocessing for a self-supervised Convolutional Neural Network and evaluating classification methods, including SVM, multilayer perceptrons, and prototypical networks. Our experiments yield an accuracy of 87.66\%, showcasing the potential of AI-driven methods to ensure the survival of historical music for future generations through advanced digital archiving techniques.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。