WakeupUrban: Unsupervised Semantic Segmentation of Mid-20^th century Urban Landscapes with Satellite Imagery

2025/06/11 by Tianxiang Hao, Hao, Tianxiang, Lixian Zhang +9 · 1 citation
Engineering · Environmental Science · Social Sciences · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Mobility and Location-Based Analysis #Land Use and Ecosystem Services #Remote-Sensing Image Classification

paper · pdf · doi:10.48550/arxiv.2506.09476

openalex publication_date 2025/06/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30

Abstract

Historical satellite imagery archive, such as Keyhole satellite data, offers rare insights into understanding early urban development and long-term transformation. However, severe quality degradation (e.g., distortion, misalignment, and spectral scarcity) and the absence of annotations have long hindered its analysis. To bridge this gap and enhance understanding of urban development, we introduce WakeupUrbanBench, an annotated segmentation dataset based on historical satellite imagery with the earliest observation time among all existing remote sensing (RS) datasets, along with a framework for unsupervised segmentation tasks, WakeupUSM. First, WakeupUrbanBench serves as a pioneer, expertly annotated dataset built on mid-20^th century RS imagery, involving four key urban classes and spanning 4 cities across 2 continents with nearly 1000 km² area of diverse urban morphologies, and additionally introducing one present-day city. Second, WakeupUSM is a novel unsupervised semantic segmentation framework for historical RS imagery. It employs a confidence-aware alignment mechanism and focal-confidence loss based on a self-supervised learning architecture, which generates robust pseudo-labels and adaptively prioritizes prediction difficulty and label reliability to improve unsupervised segmentation on noisy historical data without manual supervision. Comprehensive experiments demonstrate WakeupUSM significantly outperforms existing unsupervised segmentation methods both WakeupUrbanBench and public dataset, promising to pave the way for quantitative studies of long-term urban change using modern computer vision. Our benchmark and codes will be released at https://github.com/Tianxiang-Hao/WakeupUrban.

Citations

• DINOv3
• OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Construction
• SEN12-WATER: A New Dataset for Hydrological Applications and its Benchmarking
• Generalized Few-Shot Semantic Segmentation in Remote Sensing: Challenge and Benchmark
• Image Segmentation in Foundation Model Era: A Survey
• FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic Understanding
• Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals
• EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation
• UV-SAM: Adapting Segment Anything Model for Urban Village Identification
• GBSS:a global building semantic segmentation dataset for large-scale remote sensing building extraction
• SAM-Assisted Remote Sensing Imagery Semantic Segmentation with Object and Boundary Constraints
• AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation
• DINOv2: Learning Robust Visual Features without Supervision
• Segment Everything Everywhere All at Once
• Leveraging Hidden Positives for Unsupervised Semantic Segmentation
• A Simple Framework for Open-Vocabulary Segmentation and Detection
• Generalized Decoding for Pixel, Image, and Language
• OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping
• DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation
• Unsupervised Semantic Segmentation by Distilling Feature Correspondences
• UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery
• Emerging Properties in Self-Supervised Vision Transformers
• Hi-UCD: A Large-scale Dataset for Urban Semantic Change Detection in Remote Sensing Imagery
• Fully Convolutional Networks for Multisource Building Extraction From an Open Aerial and Satellite Imagery Data Set
• Invariant Information Clustering for Unsupervised Image Classification and Segmentation

Cited by

• Generalized Referring Expression Segmentation on Aerial Photos

Related

• FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic Understanding
• UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction
• Detection of Structural Change in Geographic Regions of Interest by Self Organized Mapping: Las Vegas City and Lake Mead across the Years
• DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding
• Cross-City Matters: A Multimodal Remote Sensing Benchmark Dataset for Cross-City Semantic Segmentation using High-Resolution Domain Adaptation Networks