Baltimore Atlas: FreqWeaver Adapter for Semi-supervised Ultra-high Spatial Resolution Land Cover Classification

TL;DR

Baltimore Atlas introduces a semi-supervised, parameter-efficient framework for ultra-high spatial resolution land cover classification, leveraging a new dataset, a specialized adapter, and unlabeled data to improve accuracy with minimal training data.

Contribution

The paper presents Baltimore Atlas, a novel UHSR land cover classification framework that reduces training data requirements using a new dataset, a FreqWeaver Adapter, and an uncertainty-aware semi-supervised approach.

Findings

Achieves 1.78% IoU improvement over existing parameter-efficient methods.

Gains 3.44% IoU over state-of-the-art high-resolution segmentation methods.

Uses only 5.96% of total model parameters.

Abstract

Ultra-high Spatial Resolution (UHSR) Land Cover Classification is increasingly important for urban analysis, enabling fine-scale planning, ecological monitoring, and infrastructure management. It identifies land cover types on sub-meter remote sensing imagery, capturing details such as building outlines, road networks, and distinct boundaries. However, most existing methods focus on 1 m imagery and rely heavily on large-scale annotations, while UHSR data remain scarce and difficult to annotate, limiting practical applicability. To address these challenges, we introduce Baltimore Atlas, a UHSR land cover classification framework that reduces reliance on large-scale training data and delivers high-accuracy results. Baltimore Atlas builds on three key ideas: (1) Baltimore Atlas Dataset, a 0.3 m resolution dataset based on aerial imagery of Baltimore City; (2) FreqWeaver Adapter, a parameter-efficient adapter that transfers SAM2 to this domain, leveraging foundation model knowledge to reduce training data needs while enabling fine-grained detail and structural modeling; (3) Uncertainty-Aware Teacher Student Framework, a semi-supervised framework that exploits unlabeled data to further reduce training dependence and improve generalization across diverse scenes. Using only 5.96% of total model parameters, our approach achieves a 1.78% IoU improvement over existing parameter-efficient tuning strategies and a 3.44% IoU gain compared to state-of-the-art high-resolution remote sensing segmentation methods on the Baltimore Atlas Dataset.