Semi-Supervised Multitask Learning on Multispectral Satellite Images Using Wasserstein Generative Adversarial Networks (GANs) for Predicting Poverty
This work addresses the challenge of estimating poverty in hard-to-survey regions like Africa, which is incremental as it builds on existing GAN and multitask learning methods.
The paper tackles the problem of predicting local poverty metrics in Africa using limited labeled data from expensive surveys by training a CNN on publicly available satellite images with only 5% labeled data, employing a semi-supervised approach with Wasserstein GANs and multitask learning to achieve improved predictions.
Obtaining reliable data describing local poverty metrics at a granularity that is informative to policy-makers requires expensive and logistically difficult surveys, particularly in the developing world. Not surprisingly, the poverty stricken regions are also the ones which have a high probability of being a war zone, have poor infrastructure and sometimes have governments that do not cooperate with internationally funded development efforts. We train a CNN on free and publicly available daytime satellite images of the African continent from Landsat 7 to build a model for predicting local economic livelihoods. Only 5% of the satellite images can be associated with labels (which are obtained from DHS Surveys) and thus a semi-supervised approach using a GAN (similar to the approach of Salimans, et al. (2016)), albeit with a more stable-to-train flavor of GANs called the Wasserstein GAN regularized with gradient penalty(Gulrajani, et al. (2017)) is used. The method of multitask learning is employed to regularize the network and also create an end-to-end model for the prediction of multiple poverty metrics.