SLUM-i: Semi-supervised Learning for Urban Mapping of Informal Settlements and Data Quality Benchmarking
🤖 AI Summary
This study addresses the challenges of mapping informal settlements—namely, scarce annotations, spectral ambiguity, and data noise—by introducing a benchmark remote sensing dataset spanning eight cities across three continents. The authors propose a novel semi-supervised semantic segmentation framework that incorporates a class-aware adaptive thresholding mechanism and a prototype feature bank to effectively mitigate class imbalance and feature degradation. Experimental results demonstrate that, using only 10% labeled data, the model achieves a mean Intersection-over-Union (mIoU) of 0.461 on unseen geographic regions, significantly outperforming fully supervised models in zero-shot generalization and exhibiting strong cross-domain recognition capabilities.
Application Category
📝 Abstract
Rapid urban expansion has fueled the growth of informal settlements in major cities of low- and middle-income countries, with Lahore and Karachi in Pakistan and Mumbai in India serving as prominent examples. However, large-scale mapping of these settlements is severely constrained not only by the scarcity of annotations but by inherent data quality challenges, specifically high spectral ambiguity between formal and informal structures and significant annotation noise. We address this by introducing a benchmark dataset for Lahore, constructed from scratch, along with companion datasets for Karachi and Mumbai, which were derived from verified administrative boundaries, totaling 1,869 $\text{km}^2$ of area. To evaluate the global robustness of our framework, we extend our experiments to five additional established benchmarks, encompassing eight cities across three continents, and provide comprehensive data quality assessments of all datasets. We also propose a new semi-supervised segmentation framework designed to mitigate the class imbalance and feature degradation inherent in standard semi-supervised learning pipelines. Our method integrates a Class-Aware Adaptive Thresholding mechanism that dynamically adjusts confidence thresholds to prevent minority class suppression and a Prototype Bank System that enforces semantic consistency by anchoring predictions to historically learned high-fidelity feature representations. Extensive experiments across a total of eight cities spanning three continents demonstrate that our approach outperforms state-of-the-art semi-supervised baselines. Most notably, our method demonstrates superior domain transfer capability whereby a model trained on only 10% of source labels reaches a 0.461 mIoU on unseen geographies and outperforms the zero-shot generalization of fully supervised models.
Problem
Research questions and friction points this paper is trying to address.
informal settlements
urban mapping
data scarcity
spectral ambiguity
annotation noise
Innovation
Methods, ideas, or system contributions that make the work stand out.
semi-supervised learning
informal settlements mapping
class-aware adaptive thresholding
prototype bank system
cross-domain generalization
🔎 Similar Papers
No similar papers found.
