Deep Active Learning: A Reality Check

arXiv:2403.14800v1 Announce Type: new
Abstract: We conduct a comprehensive evaluation of state-of-the-art deep active learning methods. Surprisingly, under general settings, no single-model method decisively outperforms entropy-based active learning, and some even fall short of random sampling. We delve into overlooked aspects like starting budget, budget step, and pretraining's impact, revealing their significance in achieving superior results. Additionally, we extend our evaluation to other tasks, exploring the active learning effectiveness in combination with semi-supervised learning, and object detection. Our experiments provide …

abstract active learning art arxiv budget check cs.ai cs.cv cs.lg entropy evaluation general impact pretraining random reality sampling significance state type