Transfer Learning of Semantic Segmentation Methods for Identifying Buried Archaeological Structures on LiDAR Data

TL;DR

This study evaluates transfer learning for semantic segmentation of LiDAR data in archaeology, showing potential performance gains but highlighting the need for further systematic improvements.

Contribution

It compares different transfer learning configurations across two neural networks and datasets, providing insights and baseline results for archaeological remote sensing.

Findings

Transfer learning can improve segmentation performance in archaeological LiDAR data.

No systematic enhancement was observed across all configurations.

Provides baseline insights for future transfer learning applications in archaeology.

Abstract

When applying deep learning to remote sensing data in archaeological research, a notable obstacle is the limited availability of suitable datasets for training models. The application of transfer learning is frequently employed to mitigate this drawback. However, there is still a need to explore its effectiveness when applied across different archaeological datasets. This paper compares the performance of various transfer learning configurations using two semantic segmentation deep neural networks on two LiDAR datasets. The experimental results indicate that transfer learning-based approaches in archaeology can lead to performance improvements, although a systematic enhancement has not yet been observed. We provide specific insights about the validity of such techniques that can serve as a baseline for future works.