论文标题
使用保形预测为图像分类器提供不确定性集
Uncertainty Sets for Image Classifiers using Conformal Prediction
论文作者
论文摘要
卷积图像分类器可以实现高预测精度，但是量化其不确定性仍然是尚未解决的挑战，阻碍了他们在结果环境中的部署。现有的不确定性量化技术（例如PLATT缩放）试图校准网络的概率估计，但它们没有正式的保证。我们提出了一种算法，该算法修改了任何分类器，以输出包含具有用户指定概率的TRUE标签的预测集，例如90％。该算法像PLATT缩放一样简单快捷，但为每个模型和数据集提供了正式的有限样本覆盖范围保证。我们的方法修改了现有的保形预测算法，从而通过在PLATT缩放后正规化不太可能的类别分数来提供更稳定的预测集。在具有RESNET-152和其他分类器的ImageNet和Imagenet-V2的实验中，我们的方案的表现优于现有方法，通过通常比独立PLATT缩放基线小的5至10个因素来实现覆盖范围。
Convolutional image classifiers can achieve high predictive accuracy, but quantifying their uncertainty remains an unresolved challenge, hindering their deployment in consequential settings. Existing uncertainty quantification techniques, such as Platt scaling, attempt to calibrate the network's probability estimates, but they do not have formal guarantees. We present an algorithm that modifies any classifier to output a predictive set containing the true label with a user-specified probability, such as 90%. The algorithm is simple and fast like Platt scaling, but provides a formal finite-sample coverage guarantee for every model and dataset. Our method modifies an existing conformal prediction algorithm to give more stable predictive sets by regularizing the small scores of unlikely classes after Platt scaling. In experiments on both Imagenet and Imagenet-V2 with ResNet-152 and other classifiers, our scheme outperforms existing approaches, achieving coverage with sets that are often factors of 5 to 10 smaller than a stand-alone Platt scaling baseline.
