论文标题
使用总和网络评估深度积极学习的不确定性
Using Sum-Product Networks to Assess Uncertainty in Deep Active Learning
论文作者
论文摘要
深度积极学习的成功取决于选择有效的采集函数，该功能尚未根据其预期的信息对数据点进行标记。许多采集功能（部分地）是基于当前模型对某个点标签具有的不确定性，但没有普遍同意计算这种不确定性的策略。本文提出了一种使用卷积神经网络（CNN）的深度积极学习中计算不确定性的新方法，以计算不确定性。主要思想是使用CNN提取的功能表示形式作为培训总产品网络（SPN）的数据。由于SPN通常用于估计数据集的分布，因此它们非常适合估算类概率的任务，这些概率可以直接由标准采集函数（例如最大熵和变异比率）直接使用。在几个标准基准数据集进行图像分类的实验研究中证明了我们方法的有效性，我们将其与评估深度活跃学习中不确定性的各种最新方法进行了比较。
The success of deep active learning hinges on the choice of an effective acquisition function, which ranks not yet labeled data points according to their expected informativeness. Many acquisition functions are (partly) based on the uncertainty that the current model has about the class label of a point, yet there is no generally agreed upon strategy for computing such uncertainty. This paper proposes a new and very simple approach to computing uncertainty in deep active learning with a Convolutional Neural Network (CNN). The main idea is to use the feature representation extracted by the CNN as data for training a Sum-Product Network (SPN). Since SPNs are typically used for estimating the distribution of a dataset, they are well suited to the task of estimating class probabilities that can be used directly by standard acquisition functions such as max entropy and variational ratio. The effectiveness of our method is demonstrated in an experimental study on several standard benchmark datasets for image classification, where we compare it to various state-of-the-art methods for assessing uncertainty in deep active learning.
