Deep Bayesian Active Learning, A Brief Survey on Recent Advances
This survey provides an overview of recent progress in Deep Bayesian Active Learning, which is important for researchers and practitioners interested in efficient data annotation and uncertainty quantification in deep learning.
This paper surveys recent advances in Deep Bayesian Active Learning (DBAL) frameworks, which address the challenge of efficient data annotation while representing model uncertainty. DBAL allows for training with small datasets and provides practical considerations for uncertainty representation, crucial for active learning.
Active learning frameworks offer efficient data annotation without remarkable accuracy degradation. In other words, active learning starts training the model with a small size of labeled data while exploring the space of unlabeled data in order to select most informative samples to be labeled. Generally speaking, representing the uncertainty is crucial in any active learning framework, however, deep learning methods are not capable of either representing or manipulating model uncertainty. On the other hand, from the real world application perspective, uncertainty representation is getting more and more attention in the machine learning community. Deep Bayesian active learning frameworks and generally any Bayesian active learning settings, provide practical consideration in the model which allows training with small data while representing the model uncertainty for further efficient training. In this paper, we briefly survey recent advances in Bayesian active learning and in particular deep Bayesian active learning frameworks.