Semi-Supervised Multitask Learning on Multispectral Satellite Images Using Wasserstein Generative Adversarial Networks (GANs) for Predicting Poverty.
Anthony PerezSwetava GanguliStefano ErmonGeorge AzzariMarshall BurkeDavid B. LobellPublished in: CoRR (2019)
Keyphrases
- multitask learning
- semi supervised
- multispectral satellite images
- generative model
- labeled data
- unsupervised learning
- multispectral
- learning tasks
- gaussian processes
- semi supervised learning
- multi task learning
- active learning
- supervised learning
- unlabeled data
- pairwise
- multi task
- topographic maps
- network structure
- learning problems
- kernel function
- gaussian process
- random sampling
- machine learning
- multi class
- image analysis
- feature selection