论文标题
通过高斯过程模型检测神经网络中的错误分类错误
Detecting Misclassification Errors in Neural Networks with a Gaussian Process Model
论文作者
论文摘要
由于神经网络分类器被部署在现实世界应用程序中，因此可以可靠地检测到它们的失败至关重要。一种实用的解决方案是为每个预测分配置信分数，然后使用这些得分来过滤可能的错误分类。但是，现有的置信度指标尚未足够可靠。本文提出了一个新框架，该框架产生了用于检测错误分类错误的定量度量。该框架（红色）在基本分类器的顶部构建了错误检测器，并使用高斯过程估算检测分数的不确定性。与125个UCI数据集上的其他错误检测方法的实验比较表明，这种方法是有效的。在两个概率基础分类器和两个大型深度学习架构中的进一步实现进一步证实了该方法是可靠且可扩展的。第三，对红色的经验分析与分布和对抗性样本表明，该方法不仅可以用于检测错误，而且可以理解它们的来源。因此，红色可以用来将来可以用来更广泛地提高神经网络分类器的可信度。
As neural network classifiers are deployed in real-world applications, it is crucial that their failures can be detected reliably. One practical solution is to assign confidence scores to each prediction, then use these scores to filter out possible misclassifications. However, existing confidence metrics are not yet sufficiently reliable for this role. This paper presents a new framework that produces a quantitative metric for detecting misclassification errors. This framework, RED, builds an error detector on top of the base classifier and estimates uncertainty of the detection scores using Gaussian Processes. Experimental comparisons with other error detection methods on 125 UCI datasets demonstrate that this approach is effective. Further implementations on two probabilistic base classifiers and two large deep learning architecture in vision tasks further confirm that the method is robust and scalable. Third, an empirical analysis of RED with out-of-distribution and adversarial samples shows that the method can be used not only to detect errors but also to understand where they come from. RED can thereby be used to improve trustworthiness of neural network classifiers more broadly in the future.
