Mapping Temporary Slums from Satellite Imagery using a Semi-Supervised Approach

TL;DR

This paper introduces a semi-supervised deep learning approach to detect temporary slums from satellite imagery, using minimal labeled data and iterative pseudo-labeling, to address the challenge of mapping these transient regions.

Contribution

The paper presents a novel semi-supervised segmentation method that automatically discovers seed samples and iteratively improves slum detection with minimal manual labeling.

Findings

Outperforms existing semi-supervised baselines in slum detection accuracy.

Constructed a large dataset of 200 temporary slum locations in Pakistan.

Demonstrates effectiveness of pseudo-labeling in transient region mapping.

Abstract

One billion people worldwide are estimated to be living in slums, and documenting and analyzing these regions is a challenging task. As compared to regular slums; the small, scattered and temporary nature of temporary slums makes data collection and labeling tedious and time-consuming. To tackle this challenging problem of temporary slums detection, we present a semi-supervised deep learning segmentation-based approach; with the strategy to detect initial seed images in the zero-labeled data settings. A small set of seed samples (32 in our case) are automatically discovered by analyzing the temporal changes, which are manually labeled to train a segmentation and representation learning module. The segmentation module gathers high dimensional image representations, and the representation learning module transforms image representations into embedding vectors. After that, a scoring module uses the embedding vectors to sample images from a large pool of unlabeled images and generates pseudo-labels for the sampled images. These sampled images with their pseudo-labels are added to the training set to update the segmentation and representation learning modules iteratively. To analyze the effectiveness of our technique, we construct a large geographically marked dataset of temporary slums. This dataset constitutes more than 200 potential temporary slum locations (2.28 square kilometers) found by sieving sixty-eight thousand images from 12 metropolitan cities of Pakistan covering 8000 square kilometers. Furthermore, our proposed method outperforms several competitive semi-supervised semantic segmentation baselines on a similar setting. The code and the dataset will be made publicly available.