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

Abstract

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.

18 pages, accepted at ICDAR2025

References in corpus (5)

• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• Self-Regularized Prototypical Network for Few-Shot Semantic Segmentation
• Efficient few-shot learning for pixel-precise handwritten document layout analysis
• Drawing the Line: Deep Segmentation for Extracting Art from Ancient Etruscan Mirrors
• Fusing Forces: Deep-Human-Guided Refinement of Segmentation Masks