Deep Bayesian Active Semi-Supervised Learning
Authors:
- Matthias RottmannMRMatthias Rottmann
- Karsten KahlKKKarsten Kahl
- Hanno GottschalkHGHanno Gottschalk
- 1 December 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 158-164
Abstract
In many applications the process of generating label information is expensive and time consuming. We present a new method that combines active and semi-supervised deep learning to achieve high generalization performance from a deep convolutional neural network with as few known labels as possible. In a setting where a small amount of labeled data as well as a large amount of unlabeled data is available, our method first learns the labeled data set. This initialization is followed by an expectation maximization algorithm, where further training reduces classification entropy on the unlabeled data by targeting a low entropy fit which is consistent with the labeled data. In addition the algorithm asks at a specified frequency an oracle for labels of data with entropy above a certain entropy quantile. Using this active learning component we obtain an agile labeling process that achieves high accuracy, but requires only a small amount of known labels. For the MNIST dataset we report an error rate of 2.06% using only 300 labels and 1.06% for 1,000 labels. These results are obtained without employing any special network architecture or data augmentation.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- On-line active learning: A new paradigm to improve practical useability of data stream modeling methodsInformation Sciences, 2017
- A Novel Active Semisupervised Convolutional Neural Network Algorithm for SAR Image RecognitionComputational Intelligence and Neuroscience, 2017
- Semi-supervised Learning Using an Unsupervised Atlas2014
- Deep Learning via Semi-supervised Embedding2012
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Rule-injection hints as a means of improving network performance and learning time1990