Misclassification detection is an important problem in machine learning, as it allows for the identification of instances where the model's predictions are unreliable. However, conventional uncertainty measures such as Shannon entropy do not provide an effective way to infer the real uncertainty associated with the model's predictions. In this paper, we introduce a novel data-driven measure of uncertainty relative to an observer for misclassification detection. By learning patterns in the distribution of soft-predictions, our uncertainty measure can identify misclassified samples based on the predicted class probabilities. Interestingly, according to the proposed measure, soft-predictions corresponding to misclassified instances can carry a large amount of uncertainty, even though they may have low Shannon entropy. We demonstrate empirical improvements over multiple image classification tasks, outperforming state-of-the-art misclassification detection methods.

翻译：误分类检测是机器学习中的一个重要问题，它能够识别模型预测不可靠的实例。然而，传统的不确定性度量（如香农熵）无法有效推断模型预测相关的真实不确定性。本文提出了一种新颖的基于数据驱动的相对不确定性度量方法，用于误分类检测。通过学习软预测分布的规律，我们的不确定性度量能够基于预测类别概率识别误分类样本。有趣的是，根据所提出的度量，对应于误分类实例的软预测可能携带大量不确定性，即便其香农熵较低。我们在多个图像分类任务上展示了实证改进，性能优于当前最先进的误分类检测方法。