Tri-net for Semi-Supervised Deep Learning

doi:10.24963/ijcai.2018/278

Tri-net for Semi-Supervised Deep Learning

2018-07-01

0

OA

AI

DOI：10.24963/ijcai.2018/278

原文链接

原文求助

摘要

En 中文

Deep neural networks have witnessed great successes in various real applications, but it requires a large number of labeled data for training. In this paper, we propose tri-net, a deep neural network which is able to use massive unlabeled data to help learning with limited labeled data. We consider model initialization, diversity augmentation and pseudo-label editing simultaneously. In our work, we utilize output smearing to initialize modules, use fine-tuning on labeled data to augment diversity and eliminate unstable pseudo-labels to alleviate the influence of suspicious pseudo-labeled data. Experiments show that our method achieves the best performance in comparison with state-of-the-art semi-supervised deep learning methods. In particular, it achieves 8.30% error rate on CIFAR-10 by using only 4000 labeled examples.

Tri-net for Semi-Supervised Deep Learning

摘要

期刊

机构

引用论文