Semi-Supervised Deep Learning Using Improved Unsupervised Discriminant Projection
This addresses the challenge of limited labeled data in applications like medical diagnosis, though it appears incremental as it builds on existing dimension reduction techniques.
The paper tackles the problem of deep learning requiring large labeled datasets by proposing a semi-supervised algorithm that uses modified unsupervised discriminant projection as a regularization term to leverage unlabeled data, achieving satisfactory classification results with only dozens of labeled samples.
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.