arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.04183cs.LGstat.ML
收藏

使用生成模型的不确定性感知深度分类器

Uncertainty-Aware Deep Classifiers using Generative Models

Blue Prism AI Labs(蓝棱镜人工智能实验室);Ozyegin University(奥兹耶金大学);US Army Research Lab(美国陆军研究实验室);University of Brescia(布雷西亚大学);Cardiff University(卡迪夫大学)

Murat Sensoy, Lance Kaplan, Federico Cerutti, Maryam Saleki

摘要:

深度神经网络通常对他们不知道的事情一无所知,并且在做出不知情的预测时过于自信。最近的一些方法通过训练模型来直接量化分类不确定性,以输出接近类边界或来自训练分布外部的数据样本的高不确定性。这些方法在训练期间使用辅助数据集来表示分布外的样本。然而,这种辅助数据集的选择或创建是不平凡的,特别是对于诸如图像的高维数据。在这项工作中,我们开发了一种新的神经网络模型,能够表达任意和认知的不确定性,区分决策边界和分布区域的特征空间。为此,将变分自编码器和生成对抗网络结合起来,自动生成用于训练的分布外样本。通过广泛的分析,我们证明了所提出的方法提供了更好的估计的不确定性的分布样本,和对抗的例子对国家的最先进的方法,包括最近的贝叶斯方法神经网络和异常检测方法的知名数据集。

英文摘要:

Deep neural networks are often ignorant about what they do not know and overconfident when they make uninformed predictions. Some recent approaches quantify classification uncertainty directly by training the model to output high uncertainty for the data samples close to class boundaries or from the outside of the training distribution. These approaches use an auxiliary data set during training to represent out-of-distribution samples. However, selection or creation of such an auxiliary data set is non-trivial, especially for high dimensional data such as images. In this work we develop a novel neural network model that is able to express both aleatoric and epistemic uncertainty to distinguish decision boundary and out-of-distribution regions of the feature space. To this end, variational autoencoders and generative adversarial networks are incorporated to automatically generate out-of-distribution exemplars for training. Through extensive analysis, we demonstrate that the proposed approach provides better estimates of uncertainty for in- and out-of-distribution samples, and adversarial examples on well-known data sets against state-of-the-art approaches including recent Bayesian approaches for neural networks and anomaly detection methods.

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。

↑