This repo consists Pytorch code for the paper Intepolation Consistency Training for Semi-supervised Learning (Insert arxiv link here)
In this paper, we propose a simple and efficient algorith for training Deep Neural Networks in the Semi-supervised setting, using interpolations between the unlabeled data samples. Our method outperforms (or is competitive with) other recent state-of-the-art methods on CIFAR10 and SVHN datasets, despite having no significant additional computation cost.
If you find this work useful and use it on your own research, please cite our [paper](inset link here).
bibtex here