Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Junhao, Stephen, Aboagye-Ntow, Wang, Chuyuan, Chen, Gang, Huang, Xin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2506.15565
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916912977412096
author Wu, Junhao
Stephen, Aboagye-Ntow
Wang, Chuyuan
Chen, Gang
Huang, Xin
author_facet Wu, Junhao
Stephen, Aboagye-Ntow
Wang, Chuyuan
Chen, Gang
Huang, Xin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15565
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Baltimore Atlas: FreqWeaver Adapter for Semi-supervised Ultra-high Spatial Resolution Land Cover Classification
Wu, Junhao
Stephen, Aboagye-Ntow
Wang, Chuyuan
Chen, Gang
Huang, Xin
Computer Vision and Pattern Recognition
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.
title Baltimore Atlas: FreqWeaver Adapter for Semi-supervised Ultra-high Spatial Resolution Land Cover Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.15565