Reliable confidence estimation for deep neural classifiers is a challenging yet fundamental requirement in high-stakes applications. Unfortunately, modern deep neural networks are often overconfident for their erroneous predictions. In this work, we exploit the easily available outlier samples, i.e., unlabeled samples coming from non-target classes, for helping detect misclassification errors. Particularly, we find that the well-known Outlier Exposure, which is powerful in detecting out-of-distribution (OOD) samples from unknown classes, does not provide any gain in identifying misclassification errors. Based on these observations, we propose a novel method called OpenMix, which incorporates open-world knowledge by learning to reject uncertain pseudo-samples generated via outlier transformation. OpenMix significantly improves confidence reliability under various scenarios, establishing a strong and unified framework for detecting both misclassified samples from known classes and OOD samples from unknown classes. The code is publicly available at https://github.com/Impression2805/OpenMix.
翻译:可靠的神经网络分类器置信度估计是高风险应用中的一项具有挑战性但基本的要求。不幸的是,现代深度神经网络通常会对其错误预测过于自信。在本文中,我们利用易于获得的异常样本,即来自非目标类的未标记样本,来帮助检测分类错误。特别地,我们发现著名的 Outlier Exposure,在检测来自未知类别的分布外样本方面非常强大,但并没有为识别分类错误提供任何帮助。基于这些观察结果,我们提出了一种名为 OpenMix 的新方法,通过学习拒绝通过异常数据转换生成的不确定伪样本,引入了开放式世界知识。OpenMix 在各种情况下都显着提高了置信度的可靠性,为检测来自已知类别的被错误分类的样本和来自未知类别的分布外样本建立了一个强大而统一的框架。代码可公开访问 https://githu