Generalizable Slum Detection from Satellite Imagery with Mixture-of-Experts
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (45) · 38826-38834
DOI: 10.1609/aaai.v40i45.41227 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Sumin Lee und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Satellite-based slum segmentation holds significant promise in generating global estimates of urban poverty. However, the morphological heterogeneity of informal settlements presents a major challenge, hindering the ability of models trained on specific regions to generalize effectively to unseen locations. To address this, we introduce a large-scale high-resolution dataset and propose GRAM (Generalized Region-Aware Mixture-of-Experts), a two-phase test-time adaptation framework that enables robust slum segmentation without requiring labeled data from target regions. We compile a million-scale satellite imagery dataset from 12 cities across four continents for source training. Using this dataset, the model employs a Mixture-of-Experts architecture to capture region-specific slum characteristics while learning universal features through a shared backbone. During adaptation, prediction consistency across experts filters out unreliable pseudo-labels, allowing the model to generalize effectively to previously unseen regions. GRAM outperforms state-of-the-art baselines in low-resource settings such as African cities, offering a scalable and label-efficient solution for global slum mapping and data-driven urban planning.
Zitieren
APA
Lee, S., Park, S., Yang, J., Kim, J., & Cha, M. (2026). Generalizable Slum Detection from Satellite Imagery with Mixture-of-Experts. Proceedings of the AAAI Conference on Artificial Intelligence, 40(45), 38826-38834. https://doi.org/10.1609/aaai.v40i45.41227
Vancouver
Lee S, Park S, Yang J, Kim J, Cha M. Generalizable Slum Detection from Satellite Imagery with Mixture-of-Experts. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(45):38826-38834. doi:10.1609/aaai.v40i45.41227
BibTeX
@article{Lee2026,
author = {Lee, Sumin and Park, Sungwon and Yang, Jeasurk and Kim, Jihee and Cha, Meeyoung},
title = {Generalizable Slum Detection from Satellite Imagery with Mixture-of-Experts},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {45},
pages = {38826--38834},
doi = {10.1609/aaai.v40i45.41227}
}
EUVIMED