A Survey on Deep Active Learning: Recent Advances and New Frontiers

arXiv:2405.00334v1 Announce Type: new
Abstract: Active learning seeks to achieve strong performance with fewer training samples. It does this by iteratively asking an oracle to label new selected samples in a human-in-the-loop manner. This technique has gained increasing popularity due to its broad applicability, yet its survey papers, especially for deep learning-based active learning (DAL), remain scarce. Therefore, we conduct an advanced and comprehensive survey on DAL. We first introduce reviewed paper collection and filtering. Second, we formally define the …

abstract active learning advances arxiv cs.lg frontiers human loop oracle papers performance samples survey training type