Semantic Segmentation for Sequential Historical Maps by Learning from Only One Map

2025-01-03

AI Summary

To address the heavy reliance on labor-intensive manual annotations in deep learning–based digitization of historical paper maps, this paper proposes a weakly supervised semantic segmentation framework. Leveraging temporal consistency in land-cover layout and visual style across adjacent-era maps, it introduces a novel “age-tracking” strategy that automatically generates cross-temporal pseudo-labels from a single annotated map. Integrated with self-training and model distillation, the method enables fully automated sequential segmentation. It overcomes the annotation bottleneck of fully supervised approaches, achieving an mIoU of 77.3% (+20% relative improvement) and an overall accuracy of 97% on the Hameln dataset—substantially outperforming existing baselines. The core contribution lies in the first formulation of temporal priors as a weak supervision signal, enabling high-accuracy, scalable digitization of historical maps from only one annotated exemplar.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Historical maps are valuable resources that capture detailed geographical information from the past. However, these maps are typically available in printed formats, which are not conducive to modern computer-based analyses. Digitizing these maps into a machine-readable format enables efficient computational analysis. In this paper, we propose an automated approach to digitization using deep-learning-based semantic segmentation, which assigns a semantic label to each pixel in scanned historical maps. A key challenge in this process is the lack of ground-truth annotations required for training deep neural networks, as manual labeling is time-consuming and labor-intensive. To address this issue, we introduce a weakly-supervised age-tracing strategy for model fine-tuning. This approach exploits the similarity in appearance and land-use patterns between historical maps from neighboring time periods to guide the training process. Specifically, model predictions for one map are utilized as pseudo-labels for training on maps from adjacent time periods. Experiments conducted on our newly curated extit{Hameln} dataset demonstrate that the proposed age-tracing strategy significantly enhances segmentation performance compared to baseline models. In the best-case scenario, the mean Intersection over Union (mIoU) achieved 77.3%, reflecting an improvement of approximately 20% over baseline methods. Additionally, the fine-tuned model achieved an average overall accuracy of 97%, highlighting the effectiveness of our approach for digitizing historical maps.

Problem

• Historical Map Digitization
• Deep Learning
• Data Annotation

Innovation

• Weakly Supervised Learning
• Deep Learning for Historical Map Digitization
• Temporal Consistency in Mapping