论文标题
改善贪婪的核心设定配置，以使用不确定性尺度的距离进行主动学习
Improving greedy core-set configurations for active learning with uncertainty-scaled distances
论文作者
论文摘要
我们通过不确定性的因素和寻找低信任配置的因素来缩放核心算法的距离，从而发现了CIFAR10/100和SVHN图像分类的样品效率的显着提高，尤其是在较大的获取尺寸中。我们展示了我们的修改的必要性，并解释了在对模型不确定性和错误分类的关系的假设下，核心损失损失收敛的概率二次加速造成的改善是如何引起的。
We scale perceived distances of the core-set algorithm by a factor of uncertainty and search for low-confidence configurations, finding significant improvements in sample efficiency across CIFAR10/100 and SVHN image classification, especially in larger acquisition sizes. We show the necessity of our modifications and explain how the improvement is due to a probabilistic quadratic speed-up in the convergence of core-set loss, under assumptions about the relationship of model uncertainty and misclassification.
