# ICDAR 2021 Competition on Historical Map Segmentation

arXiv: https://arxiv.org/abs/2105.13265 · HTML: https://mlsanity.com/paper/2105.13265/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 15 references that are in the map.
- First posted on arXiv 27 May 2021.

## Builds on (most cited first, 4 of 4)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)

## Built on by (most cited first, 5 of 5)

- [MapSAM: Adapting Segment Anything Model for Automated Feature Detection in Historical Maps](https://mlsanity.com/paper/2411.06971/) (2024)
- [Few-Shot Segmentation of Historical Maps via Linear Probing of Vision Foundation Models](https://mlsanity.com/paper/2506.21826/) (2025)
- [MapSAM2: Adapting SAM2 for Automatic Segmentation of Historical Map Images and Time Series](https://mlsanity.com/paper/2510.27547/) (2025)
- [BuyTheDips: PathLoss for improved topology-preserving deep learning-based image segmentation](https://mlsanity.com/paper/2207.11446/) (2022)
- [Linear Object Detection in Document Images using Multiple Object Tracking](https://mlsanity.com/paper/2305.16968/) (2023)

## Abstract (arXiv)

This paper presents the final results of the ICDAR 2021 Competition on Historical Map Segmentation (MapSeg), encouraging research on a series of historical atlases of Paris, France, drawn at 1/5000 scale between 1894 and 1937. The competition featured three tasks, awarded separately. Task~1 consists in detecting building blocks and was won by the L3IRIS team using a DenseNet-121 network trained in a weakly supervised fashion. This task is evaluated on 3 large images containing hundreds of shapes to detect. Task~2 consists in segmenting map content from the larger map sheet, and was won by the UWB team using a U-Net-like FCN combined with a binarization method to increase detection edge accuracy. Task~3 consists in locating intersection points of geo-referencing lines, and was also won by the UWB team who used a dedicated pipeline combining binarization, line detection with Hough transform, candidate filtering, and template matching for intersection refinement. Tasks~2 and~3 are evaluated on 95 map sheets with complex content. Dataset, evaluation tools and results are available under permissive licensing at urlhttps://icdar21-mapseg.github.io/.