用点云网络自动分类楔形文字泥板元数据，解决专家不足难题
A novel network for classification of cuneiform tablet metadata
- 设计类卷积架构逐步降采样点云并融合局部邻域信息
- 在有限标注数据下性能超越Point-BERT等先进模型
- 适合对古文字数字化与自动化分析感兴趣的学者
本文提出一种用于楔形文字泥板元数据分类的新型网络结构。该任务具有实际意义，因现有文献库规模远超可用专家数量，但受限于标注数据稀少及每块泥板高分辨率点云表示，分类难度大。为此，我们设计了一种类卷积架构，逐步降采样点云并整合局部邻近信息；随后在特征空间计算邻居，引入全局上下文信息。实验表明，该方法在多个指标上均优于当前最优的基于Transformer的Point-BERT模型。源代码与数据已公开于github.com/fhagelskjaer/cuneiform3d。
原文摘要 · Abstract (English)
In this paper, we present a network structure for classifying metadata of cuneiform tablets. The problem is of practical importance, as the size of the existing corpus far exceeds the number of experts available to analyze it. But the task is made difficult by the combination of limited annotated datasets and the high-resolution point-cloud representation of each tablet. To address this, we develop a convolution-inspired architecture that gradually down-scales the point cloud while integrating local neighbor information. The final down-scaled point cloud is then processed by computing neighbors in the feature space to include global information. Our method is compared with the state-of-the-art transformer-based network Point-BERT, and consistently obtains the best performance. Source code and data available at github.com/fhagelskjaer/cuneiform3d
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。