Separate sampling based on uncertainty often results in sampling bias, the currently selected sample is not representative of the distribution of unlabeled datasets.

University of Michigan - Ann Arbor

1. Uncertainty-based Strategy.
2. Diversity-based Strategy.
3. Expected Model Change.

Query Strategy Categories of Active Learning

A Survey of Deep Active Learning

The Disadvantage of Uncertainty-based Strategy

Considering only strategies that promote diversity in sampling may lead to increased labeling costs, as maybe a considerable number of samples with low information content will consequently be selected.

Learn Before

Related