The use of relative attributes for semantic understanding of images and videos is a promising way to improve communication between humans and machines. However, it is extremely labor- and time-consuming to define multiple attributes for each instance in large amount of data. One option is to incorporate active learning, so that the informative samples can be actively discovered and then labeled. However, most existing active-learning methods select samples one at a time (serial mode), and may therefore lose efficiency when learning multiple attributes. In this paper, we propose a batch-mode active-learning method, called diverse expected gradient active learning. This method integrates an informativeness analysis and a diversity analysis to form a diverse batch of queries. Specifically, the informativeness analysis employs the expected pairwise gradient length as a measure of informativeness, while the diversity analysis forces a constraint on the proposed diverse gradient angle. Since simultaneous optimization of these two parts is intractable, we utilize a two-step procedure to obtain the diverse batch of queries. A heuristic method is also introduced to suppress imbalanced multiclass distributions. Empirical evaluations of three different databases demonstrate the effectiveness and efficiency of the proposed approach.

中文翻译：

---

相对属性的各种期望梯度主动学习。

使用相对属性来对图像和视频进行语义理解是改善人机之间通信的一种有前途的方式。但是，为大量数据中的每个实例定义多个属性非常耗时且费时。一种选择是合并主动学习，以便可以主动发现信息样本并对其进行标记。但是，大多数现有的主动学习方法一次选择一个样本（串行模式），因此在学习多个属性时可能会失去效率。在本文中，我们提出了一种批处理模式主动学习方法，称为多样期望梯度主动学习。该方法集成了信息分析和多样性分析，以形成各种各样的查询。特别，信息性分析采用预期的成对梯度长度作为信息性的度量，而多样性分析则对建议的多样性梯度角施加了约束。由于这两个部分的同时优化是很棘手的，因此我们采用两步过程来获取不同批次的查询。还引入了一种启发式方法来抑制不平衡的多类分布。对三个不同数据库的实证评估表明了该方法的有效性和效率。还引入了一种启发式方法来抑制不平衡的多类分布。对三个不同数据库的实证评估表明了该方法的有效性和效率。还引入了一种启发式方法来抑制不平衡的多类分布。对三个不同数据库的实证评估表明了该方法的有效性和效率。