论文标题
信息凝结积极学习
Information Condensing Active Learning
论文作者
论文摘要
我们介绍信息凝结活跃学习（ICAL），这是一种针对深贝叶斯主动学习的批处理模式不可知的主动学习（AL）方法，该方法着重于获取标签的点，这些点具有尽可能多的有关仍然不再需要点数的信息。 ICAL使用Hilbert Schmidt独立标准（HSIC）来测量候选点批次批次与未标记集之间的依赖性强度。我们开发关键优化，使我们能够将方法扩展到大型未标记的集合。与最先进的方法相比，我们在几个图像数据集上的模型准确性和负模式（NLL）方面显示出显着改善。
We introduce Information Condensing Active Learning (ICAL), a batch mode model agnostic Active Learning (AL) method targeted at Deep Bayesian Active Learning that focuses on acquiring labels for points which have as much information as possible about the still unacquired points. ICAL uses the Hilbert Schmidt Independence Criterion (HSIC) to measure the strength of the dependency between a candidate batch of points and the unlabeled set. We develop key optimizations that allow us to scale our method to large unlabeled sets. We show significant improvements in terms of model accuracy and negative log likelihood (NLL) on several image datasets compared to state of the art batch mode AL methods for deep learning.
