Semi-Supervised Deep Learning Using Improved Unsupervised Discriminant Projection

Abstract

Deep learning demands a huge amount of well-labeled data to train the network parameters. How to use the least amount of labeled data to obtain the desired classification accuracy is of great practical significance, because for many real-world applications (such as medical diagnosis), it is difficult to obtain so many labeled samples. In this paper, modify the unsupervised discriminant projection algorithm from dimension reduction and apply it as a regularization term to propose a new semi-supervised deep learning algorithm, which is able to utilize both the local and nonlocal distribution of abundant unlabeled samples to improve classification performance. Experiments show that given dozens of labeled samples, the proposed algorithm can train a deep network to attain satisfactory classification results.

arXiv comment1 figures

References in corpus (7)

• Semi-Supervised Learning with Deep Generative Models
• Semi-Supervised Learning with Ladder Networks
• Learning with Pseudo-Ensembles
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• Revisiting Semi-Supervised Learning with Graph Embeddings
• Semi-supervised deep learning by metric embedding
• Semi-Supervised Phone Classification using Deep Neural Networks and Stochastic Graph-Based Entropic Regularization