SoQal: Selective Oracle Questioning for Consistency Based Active Learning of Cardiac Signals
This work addresses the burden on physicians for labeling data in clinical applications, but it is incremental as it builds on existing active learning approaches.
The paper tackles the problem of limited labeled data in clinical settings by proposing an active learning framework that jointly addresses instance acquisition and annotation, showing that their acquisition method outperforms BALD and their annotation method outperforms baselines even with noisy oracles.
Clinical settings are often characterized by abundant unlabelled data and limited labelled data. This is typically driven by the high burden placed on oracles (e.g., physicians) to provide annotations. One way to mitigate this burden is via active learning (AL) which involves the (a) acquisition and (b) annotation of informative unlabelled instances. Whereas previous work addresses either one of these elements independently, we propose an AL framework that addresses both. For acquisition, we propose Bayesian Active Learning by Consistency (BALC), a sub-framework which perturbs both instances and network parameters and quantifies changes in the network output probability distribution. For annotation, we propose SoQal, a sub-framework that dynamically determines whether, for each acquired unlabelled instance, to request a label from an oracle or to pseudo-label it instead. We show that BALC can outperform start-of-the-art acquisition functions such as BALD, and SoQal outperforms baseline methods even in the presence of a noisy oracle.