Deep Bayesian Active Learning with Image Data
arXiv:1703.02910
Abstract
Even though active learning forms an important pillar of machine learning, deep learning tools are not prevalent within it. Deep learning poses several difficulties when used in an active learning setting. First, active learning (AL) methods generally rely on being able to learn and update models from small amounts of data. Recent advances in deep learning, on the other hand, are notorious for their dependence on large amounts of data. Second, many AL acquisition functions rely on model uncertainty, yet deep learning methods rarely represent such model uncertainty. In this paper we combine recent advances in Bayesian deep learning into the active learning framework in a practical way. We develop an active learning framework for high dimensional data, a task which has been extremely challenging so far, with very sparse existing literature. Taking advantage of specialised models such as Bayesian convolutional neural networks, we demonstrate our active learning techniques with image data, obtaining a significant improvement on existing active learning approaches. We demonstrate this on both the MNIST dataset, as well as for skin cancer diagnosis from lesion images (ISIC2016 task).
References in corpus (2)
Cited by in corpus (10)
- Half a Percent of Labels is Enough: Efficient Animal Detection in UAV Imagery using Deep CNNs and Active Learning
- Discriminative Active Learning
- Deep Active Learning over the Long Tail
- TensorLayer: A Versatile Library for Efficient Deep Learning Development
- Model Selection in Bayesian Neural Networks via Horseshoe Priors
- Active Learning for Visual Question Answering: An Empirical Study
- Deep Active Learning for Axon-Myelin Segmentation on Histology Data
- Bayesian Semisupervised Learning with Deep Generative Models
- Episode-Based Active Learning with Bayesian Neural Networks
- Alpha-Divergences in Variational Dropout