Papers related to the use of unlabeled data for improving performance of classifiers in a semi-supervised setting
-
Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. [pdf]
-
Learning with pseudo-ensembles. [pdf]
-
Semisupervised learning with deep generative models. [pdf]
-
Regularization with stochastic transformations and perturbations for deep semi-supervised learning. [pdf]
-
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. [pdf]