Few-Shot Segmentation of Historical Maps via Linear Probing of Vision Foundation Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sterzinger, Rafael, Peer, Marco, Sablatnig, Robert
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914097592795136
author Sterzinger, Rafael
Peer, Marco
Sablatnig, Robert
author_facet Sterzinger, Rafael
Peer, Marco
Sablatnig, Robert
contents As rich sources of history, maps provide crucial insights into historical changes, yet their diverse visual representations and limited annotated data pose significant challenges for automated processing. We propose a simple yet effective approach for few-shot segmentation of historical maps, leveraging the rich semantic embeddings of large vision foundation models combined with parameter-efficient fine-tuning. Our method outperforms the state-of-the-art on the Siegfried benchmark dataset in vineyard and railway segmentation, achieving +5% and +13% relative improvements in mIoU in 10-shot scenarios and around +20% in the more challenging 5-shot setting. Additionally, it demonstrates strong performance on the ICDAR 2021 competition dataset, attaining a mean PQ of 67.3% for building block segmentation, despite not being optimized for this shape-sensitive metric, underscoring its generalizability. Notably, our approach maintains high performance even in extremely low-data regimes (10- & 5-shot), while requiring only 689k trainable parameters - just 0.21% of the total model size. Our approach enables precise segmentation of diverse historical maps while drastically reducing the need for manual annotations, advancing automated processing and analysis in the field. Our implementation is publicly available at: https://github.com/RafaelSterzinger/few-shot-map-segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21826
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Few-Shot Segmentation of Historical Maps via Linear Probing of Vision Foundation Models
Sterzinger, Rafael
Peer, Marco
Sablatnig, Robert
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
As rich sources of history, maps provide crucial insights into historical changes, yet their diverse visual representations and limited annotated data pose significant challenges for automated processing. We propose a simple yet effective approach for few-shot segmentation of historical maps, leveraging the rich semantic embeddings of large vision foundation models combined with parameter-efficient fine-tuning. Our method outperforms the state-of-the-art on the Siegfried benchmark dataset in vineyard and railway segmentation, achieving +5% and +13% relative improvements in mIoU in 10-shot scenarios and around +20% in the more challenging 5-shot setting. Additionally, it demonstrates strong performance on the ICDAR 2021 competition dataset, attaining a mean PQ of 67.3% for building block segmentation, despite not being optimized for this shape-sensitive metric, underscoring its generalizability. Notably, our approach maintains high performance even in extremely low-data regimes (10- & 5-shot), while requiring only 689k trainable parameters - just 0.21% of the total model size. Our approach enables precise segmentation of diverse historical maps while drastically reducing the need for manual annotations, advancing automated processing and analysis in the field. Our implementation is publicly available at: https://github.com/RafaelSterzinger/few-shot-map-segmentation.
title Few-Shot Segmentation of Historical Maps via Linear Probing of Vision Foundation Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.21826