# Deep Bayesian Active Semi-Supervised Learning

arXiv: https://arxiv.org/abs/1803.01216 · HTML: https://mlsanity.com/paper/1803.01216/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2018.

## Built on by (most cited first, 7 of 7)

- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Making Better Use of Unlabelled Data in Bayesian Active Learning](https://mlsanity.com/paper/2404.17249/) (2024)
- [Semi-supervised domain adaptation with CycleGAN guided by a downstream task loss](https://mlsanity.com/paper/2208.08815/) (2022)
- [Model Composition: Can Multiple Neural Networks Be Combined into a Single Network Using Only Unlabeled Data?](https://mlsanity.com/paper/2110.10369/) (2021)
- [AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language Models](https://mlsanity.com/paper/2112.08787/) (2021)
- [Confidence-Aware Active Feedback for Interactive Instance Search](https://mlsanity.com/paper/2110.12255/) (2021)
- [Uncertainty-Guided Edge Learning for Deep Image Regression in Remote Sensing](https://mlsanity.com/paper/2605.05590/) (2026)

## Abstract (arXiv)

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 1000 labels. These results are obtained without employing any special network architecture or data augmentation.