Abstract

The recent success of deep neural networks is attributed in part to large-scale well-labeled training data. However, with the ever-increasing size of modern datasets, combined with the difficulty of obtaining label information, semi-supervised learning (SSL) has become one of the most remarkable issues in data analysis. In this paper, we propose an Incremental Self-Labeling strategy for SSL based on Generative Adversarial Nets (ISL-GAN), which functions by constantly assigning unlabeled data with virtual labels for promoting the training process. Specifically, during the virtual labeling process, we introduce a temporal-based self-labeling strategy for safe and stable data labeling. Then, to dynamically assign more virtual labels to data during the training, we conduct a phased incremental label screening and updating strategy. Finally, to balance the contribution of samples with different loss during the training process, we further introduce the Balance factor Term (BT). The experimental results show that the proposed method gives rise to state-of-the-art semi-supervised learning results for the MNIST, CIFAR-10, and SVHN datasets. Particularly, our model performs well with fewer labeled conditions. With a dataset of only 1,000 labeled CIFAR-10 images with CONV-Large Net, a test error of 11.2% can be achieved, and nearly the same performance with a 3.5% test error can be achieved with both 500 and 1,000 image-labeled SVHN datasets.

Highlights

  • With the rapid development of deep learning [1], its application scenarios continue to expand

  • CONSISTENCY-BASED MODELS We briefly review semi-supervised learning with consistency-based models

  • The code will be available soon after the paper is accepted to facilitate the reproducibility of our results

Read more

Summary

Introduction

With the rapid development of deep learning [1], its application scenarios continue to expand. The strict requirement of data volume has become a crucial issue for the further application of deep learning. In medical image classification [2] and railway fault detection [3], [4], the training data are often much too difficult to obtain and are expensive to properly annotate. Research on techniques such as efficient feature extraction [5], [6], deep transfer learning [7], and semi-supervised deep learning (SSL) [8] are key to further promoting the effective application of deep learning. Semi-supervised learning (SSL) is a method that relieves the inefficiencies in data collection and annotation and utilizes both labeled and unlabeled data in the learning process.

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call