arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2206.09798cs.LGcs.ITmath.IT
收藏

使用和积网络评估深度主动学习中的不确定性

Using Sum-Product Networks to Assess Uncertainty in Deep Active Learning

University of Regina(里贾纳大学)

Mohamadsadegh Khosravani, Sandra Zilles

AI总结:

针对深度主动学习中不确定性计算缺乏公认策略的问题,提出用CNN提取的特征训练SPN以估计类别概率,供标准采集函数使用,经多基准数据集实验验证了有效性。

摘要:

深度主动学习的成功取决于有效采集函数的选择,该函数会根据未标记数据点的预期信息量对其进行排序。许多采集函数(部分)基于当前模型对数据点类别标签的不确定性,但目前尚无公认的计算此类不确定性的策略。本文提出了一种全新且极为简便的方法,用于计算卷积神经网络(CNN)深度主动学习中的不确定性。其核心思路是将CNN提取的特征表示作为训练和积网络(SPN)的数据。由于SPN通常用于估计数据集的分布,因此非常适合估计类别概率的任务,这些概率可直接供最大熵、变分比等标准采集函数使用。我们在多个图像分类标准基准数据集上开展了实验研究,将该方法与多种评估深度主动学习不确定性的前沿方法进行了对比,验证了方法的有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑