# Generalizable Multiscale Segmentation of Heterogeneous Map Collections

arXiv: https://arxiv.org/abs/2603.05037 · HTML: https://mlsanity.com/paper/2603.05037/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 61 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation](https://mlsanity.com/paper/1909.11065/) (2019)
- [Line Segment Detection Using Transformers without Edges](https://mlsanity.com/paper/2101.01909/) (2021)
- [Transferring Multiscale Map Styles Using Generative Adversarial Networks](https://mlsanity.com/paper/1905.02200/) (2019)
- [Synthetic Map Generation to Provide Unlimited Training Data for Historical Map Text Detection](https://mlsanity.com/paper/2112.06104/) (2021)
- [The mapKurator System: A Complete Pipeline for Extracting and Linking Text from Historical Maps](https://mlsanity.com/paper/2306.17059/) (2023)
- [Cross-attention Spatio-temporal Context Transformer for Semantic Segmentation of Historical Maps](https://mlsanity.com/paper/2310.12616/) (2023)
- [MapSAM: Adapting Segment Anything Model for Automated Feature Detection in Historical Maps](https://mlsanity.com/paper/2411.06971/) (2024)
- [MapReader: A Computer Vision Pipeline for the Semantic Exploration of Maps at Scale](https://mlsanity.com/paper/2111.15592/) (2021)
- [Towards the automated large-scale reconstruction of past road networks from historical maps](https://mlsanity.com/paper/2202.04883/) (2022)
- [Semantic Segmentation for Sequential Historical Maps by Learning from Only One Map](https://mlsanity.com/paper/2501.01845/) (2025)
- [Studying Maps at Scale: A Digital Investigation of Cartography and the Evolution of Figuration](https://mlsanity.com/paper/2511.19538/) (2025)
- [AI-driven Structure Detection and Information Extraction from Historical Cadastral Maps (Early 19th Century Franciscean Cadastre in the Province of Styria) and Current High-resolution Satellite and Aerial Imagery for Remote Sensing](https://mlsanity.com/paper/2312.07560/) (2023)
- [Probabilistic road classification in historical maps using synthetic data and deep learning](https://mlsanity.com/paper/2410.02250/) (2024)
- [Neural networks for semantic segmentation of historical city maps: Cross-cultural performance and the impact of figurative diversity](https://mlsanity.com/paper/2101.12478/) (2021)

## Abstract (arXiv)

Historical map collections are highly diverse in style, scale, and geographic focus, often consisting of many single-sheet documents. Yet most work in map recognition focuses on specialist models tailored to homogeneous map series. In contrast, this article aims to develop generalizable semantic segmentation models and ontology. First, we introduce Semap, a new open benchmark dataset comprising 1,439 manually annotated patches designed to reflect the variety of historical map documents. Second, we present a segmentation framework that combines procedural data synthesis with multiscale integration to improve robustness and transferability. This framework achieves state-of-the-art performance on both the HCMSSD and Semap datasets, showing that a diversity-driven approach to map recognition is not only viable but also beneficial. The results indicate that segmentation performance remains largely stable across map collections, scales, geographic regions, and publication contexts. By proposing benchmark datasets and methods for the generic segmentation of historical maps, this work opens the way to integrating the long tail of cartographic archives to historical geographic studies.