Journal
NEURAL NETWORKS
Volume 145, Issue -, Pages 90-106Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2021.10.008
Keywords
Semi-supervised learning; Deep Neural Networks; Mixup; Consistency regularization
Funding
- Academy of Finland Flagship programme: Finnish Center for Artificial Intelligence (FCAI)
Ask authors/readers for more resources
Interpolation Consistency Training (ICT) is a simple and efficient algorithm for training Deep Neural Networks in the semi-supervised learning paradigm, which moves the decision boundary to low-density regions of the data distribution in classification problems. Experimental results show that ICT achieves state-of-the-art performance when applied to CIFAR-10 and SVHN benchmark datasets.
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. Our theoretical analysis shows that ICT corresponds to a certain type of data-adaptive regularization with unlabeled points which reduces overfitting to labeled points under high confidence values. (C) 2021 The Authors. Published by Elsevier Ltd.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available