Domain adaptive active learning is leading the charge in label-efficient training of neural networks. For semantic segmentation, state-of-the-art models jointly use two criteria of uncertainty and diversity to select training labels, combined with a pixel-wise acquisition strategy. However, we show that such methods currently suffer from a class imbalance issue which degrades their performance for larger active learning budgets. We then introduce Class Balanced Dynamic Acquisition (CBDA), a novel active learning method that mitigates this issue, especially in high-budget regimes. The more balanced labels increase minority class performance, which in turn allows the model to outperform the previous baseline by 0.6, 1.7, and 2.4 mIoU for budgets of 5%, 10%, and 20%, respectively. Additionally, the focus on minority classes leads to improvements of the minimum class performance of 0.5, 2.9, and 4.6 IoU respectively. The top-performing model even exceeds the fully supervised baseline, showing that a more balanced label than the entire ground truth can be beneficial.

翻译：域自适应主动学习引领了神经网络标签高效训练的前沿。在语义分割任务中，现有最优模型联合使用不确定性与多样性两个准则选择训练标签，并结合像素级获取策略。然而，我们证明这类方法当前存在类别不平衡问题，该问题在更大主动学习预算下会降低其性能。为此，我们提出类别平衡动态获取（CBDA），一种新型主动学习方法，可缓解该问题，尤其在预算充足时表现突出。更平衡的标签提升了少数类性能，使模型在5%、10%和20%预算下分别比先前基线高出0.6、1.7和2.4 mIoU。此外，对少数类的关注使最低类别性能分别提升0.5、2.9和4.6 IoU。表现最佳的模型甚至超越了全监督基线，表明比完整真实标注更平衡的标签可能更具优势。