Pseudo-label Selection for Deep Semi-supervised Learning
Authors:
- 18 December 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Deep semi-supervised learning is a hot research topic in recent years. The main challenges are the small sample learning and make full use of unlabeled data. Pseudo-labeling is a simple yet effective approach in semi-supervised learning. However, how to obtain high quality pseudo-labeled data is key issue. When pseudo-labeled data with low confidence level are used to train deep learning model will enlarge or spread classification errors. To overcome this issue, we propose a confidence-based pseudo-labeling method to choose high quality pseudo-labels with a novel uncertainty model. Specifically, we treat the uncertainty of pseudo-labels as a random variable and model proposed to estimate the confidence level of the pseudo-labels. The selected pseudo-labeled data are produced by minimizing the average risk criterion. Experimental results on the MNIST dataset show that the proposed method is able to improve the performance for deep semi-supervised learning.Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 8 references indexed in Scilit:
- Deep Bayesian Self-TrainingNeural Computing and Applications, 2019
- Label Propagation for Deep Semi-Supervised Learning2019
- Deep Bayesian Active Semi-Supervised Learning2018
- Improved Training for Self Training by Confidence Assessments2018
- Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Bayesian Learning for Neural Networks1996
- A Practical Bayesian Framework for Backpropagation NetworksNeural Computation, 1992
- Bayesian InterpolationNeural Computation, 1992