Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization
Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization
复制标题
DOI：
10.1007/s11263-014-0781-x
复制
发表时间：
2015-06
影响因子：
19.5
通讯作者：
Yi Yang;Zhigang Ma;F. Nie;Xiaojun Chang;Alexander Hauptmann
中科院分区：
文献类型：
--
作者：
Yi Yang;Zhigang Ma;F. Nie;Xiaojun Chang;Alexander Hauptmann
主动学习作为一种解除人工标注繁琐工作的方法，在视觉概念识别的许多应用中发挥着重要的作用。在典型的主动学习场景中，种子集中的标记数据数量通常很少。然而，现有的主动学习算法大多只利用带标签的数据，由于带标签的样本数量较少，往往会出现过度拟合的问题。此外，尽管双班式主动学习已经取得了很大的进展，但对多班级主动学习的研究却很少。本文提出了一种用于视觉概念识别的半监督批处理模式多类主动学习算法。我们的算法利用整个活跃池来评估数据的不确定性。考虑到不确定数据总是彼此相似，我们提出了尽可能地使所选数据多样化，为此我们明确地对目标函数施加了多样性约束。作为一种多类主动学习算法，我们的算法能够利用多类之间的不确定性。采用一种高效的算法对目标函数进行优化。在动作识别、目标分类、场景识别和事件检测等方面的大量实验证明了该方法的优越性。
As a way to relieve the tedious work of manual annotation, active learning plays important roles in many applications of visual concept recognition. In typical active learning scenarios, the number of labelled data in the seed set is usually small. However, most existing active learning algorithms only exploit the labelled data, which often suffers from over-fitting due to the small number of labelled examples. Besides, while much progress has been made in binary class active learning, little research attention has been focused on multi-class active learning. In this paper, we propose a semi-supervised batch mode multi-class active learning algorithm for visual concept recognition. Our algorithm exploits the whole active pool to evaluate the uncertainty of the data. Considering that uncertain data are always similar to each other, we propose to make the selected data as diverse as possible, for which we explicitly impose a diversity constraint on the objective function. As a multi-class active learning algorithm, our algorithm is able to exploit uncertainty across multiple classes. An efficient algorithm is used to optimize the objective function. Extensive experiments on action recognition, object classification, scene recognition, and event detection demonstrate its advantages.