Interpolation Consistency Training for Semi-Supervised Learning

Understand

We introduce Interpolation Consistency Training (ICT), a simple and computation efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm.

• ICT encourages the prediction at an interpolation of unlabeled points to be consistent with the interpolation of the predictions at those points.
• In classification problems, ICT moves the decision boundary to low-density regions of the data distribution.
• Our experiments show that ICT achieves state-of-the-art performance when applied to standard neural network architectures on the CIFAR-10 and SVHN benchmark datasets.