Semi-Supervised Learning with Uncertainty
- 1 July 2018
- journal article
- Published by Japanese Society for Artificial Intelligence in Transactions of the Japanese Society for Artificial Intelligence
- Vol. 33 (4)
- https://doi.org/10.1527/tjsai.c-ha2
Abstract
The goal of semi-supervised learning is to utilize many unlabeled samples under a situation where a few labeled samples exist. Recently, researches of semi-supervised learning are evolving with deep learning technology development, because, in deep, models have powerful representation to make use of abundant unlabeled samples. In this paper, we propose a novel semi-supervised learning method with uncertainty. It naturally extends the consistency loss under the uncertainty and propose suitable regularizations for the uncertainty. Using two datasets CIFAR-10 and SVHN and with various experiments, we empirically demonstrate that the proposed method achieves competitive or higher performance in accuracy when compared to semi-supervised learning with the conventional consistency loss while our proposal can let a model generalize much faster.Keywords
This publication has 5 references indexed in Scilit:
- Manifold-Regularized Minimax Probability MachineLecture Notes in Computer Science, 2012
- Graph-Based Transduction with ConfidenceLecture Notes in Computer Science, 2012
- Manifold Coarse Graining for Online Semi-supervised LearningLecture Notes in Computer Science, 2011
- Introduction to Semi-Supervised LearningSynthesis Lectures on Artificial Intelligence and Machine Learning, 2009
- Extracting and composing robust features with denoising autoencodersPublished by Association for Computing Machinery (ACM) ,2008