论文标题
通过置信度估计不确定性感知到的迪里奇网络的失败预测
Failure Prediction by Confidence Estimation of Uncertainty-Aware Dirichlet Networks
论文作者
论文摘要
可靠地评估模型对深度学习的信心并预测可能发生的错误是为模型部署提供安全的关键要素，尤其是针对可怕后果的应用。在本文中，首先表明，不确定性意识到的深度迪里奇神经网络在真实类概率（TCP）度量中正确的预测和错误预测之间提供了改善的分离。其次，由于在测试时间未知类别，因此提出了一个新的标准，用于通过匹配预测置信度得分来学习真实类别的概率，同时考虑不平衡和TCP约束，以解决正确的预测和失败。实验结果表明，在具有各种网络体系结构的几个图像分类任务上，我们的最大类概率（MCP）基线的最大类概率（MCP）基线改善了我们的方法。
Reliably assessing model confidence in deep learning and predicting errors likely to be made are key elements in providing safety for model deployment, in particular for applications with dire consequences. In this paper, it is first shown that uncertainty-aware deep Dirichlet neural networks provide an improved separation between the confidence of correct and incorrect predictions in the true class probability (TCP) metric. Second, as the true class is unknown at test time, a new criterion is proposed for learning the true class probability by matching prediction confidence scores while taking imbalance and TCP constraints into account for correct predictions and failures. Experimental results show our method improves upon the maximum class probability (MCP) baseline and predicted TCP for standard networks on several image classification tasks with various network architectures.
