Researchers have considered using generative networks for data augmentation or assigning pseudo-labels to high-confidence samples to expand the labeled training set. Some researchers have also used labeled and unlabeled datasets to combine supervised and semisupervised training across AL cycles.

Methods to Tackle Insufficient Data for Labeled Samples.

AL often relies on a small amount of labeled sample data to learn and update the model, while DL is often very greedy for data. Data for every iteration may not be enough to train a good model.

University of Michigan - Ann Arbor

1. Model uncertainty in Deep Learning. 
2. Insufficient data for labeled samples.
3. Processing pipeline inconsistency.

Challenges of Combining Deep Learning and Active Learning

A Survey of Deep Active Learning

The SR(Softmax Response) layer's output can be too confident so that it is unreliable as a measure of confidence and the performance of this method will thus be even worse than that of random sampling.

Model Uncertainty in Deep Learning for Active Learning

Insufficient Data for Labeled Samples.

The processing pipelines of AL and DL are inconsistent. Most AL algorithms focus primarily on the training of classifiers and the various query strategies utilized are largely based on fixed feature representations.

Learn Before

Related

Learn After