Deep learning classification of large-scale point clouds: A case study on cuneiform tablets

TL;DR

This paper presents a new deep learning network architecture for classifying large-scale point clouds, specifically applied to cuneiform tablets, achieving state-of-the-art results and offering insights into feature focus through visualization.

Contribution

The paper introduces a novel network architecture for large-scale point cloud classification and applies it to cuneiform tablet metadata, demonstrating promising results and new visualization techniques.

Findings

Achieved state-of-the-art classification performance on cuneiform tablet data.

Introduced the Maximum Attention visualization to interpret network focus.

Showed promising results on new metadata classification tasks.

Abstract

This paper introduces a novel network architecture for the classification of large-scale point clouds. The network is used to classify metadata from cuneiform tablets. As more than half a million tablets remain unprocessed, this can help create an overview of the tablets. The network is tested on a comparison dataset and obtains state-of-the-art performance. We also introduce new metadata classification tasks on which the network shows promising results. Finally, we introduce the novel Maximum Attention visualization, demonstrating that the trained network focuses on the intended features. Code available at https://github.com/fhagelskjaer/dlc-cuneiform