论文标题
通过测试时数据实践估计分类置信度估算
Classification Confidence Estimation with Test-Time Data-Augmentation
论文作者
论文摘要
机器学习在我们生活的许多方面（包括医学，运输，安全，正义和其他领域）中起着越来越重要的作用，从而使虚假预测的潜在后果越来越毁灭性。如果我们能自动标记这样的错误预测并将其分配给替代性，更可靠的机制，这些后果可能会更加昂贵并涉及人类的关注，则可能会减轻这些后果。这表明检测错误的任务，我们在本文中解决了视觉分类的情况。为此，我们提出了一种新型的分类置信度估计方法。我们将一组传播语义的图像转换应用于输入图像，并展示如何使用所得图像集来估计分类器预测的信心。我们通过在各种分类器架构和数据集上进行广泛评估，从而证明了我们的方法的潜力，包括Resnext/Imagenet，可实现最新的性能。本文构成了我们早期在这个方向上的工作的重大修订（Bahat＆Shakhnarovich，2018年）。
Machine learning plays an increasingly significant role in many aspects of our lives (including medicine, transportation, security, justice and other domains), making the potential consequences of false predictions increasingly devastating. These consequences may be mitigated if we can automatically flag such false predictions and potentially assign them to alternative, more reliable mechanisms, that are possibly more costly and involve human attention. This suggests the task of detecting errors, which we tackle in this paper for the case of visual classification. To this end, we propose a novel approach for classification confidence estimation. We apply a set of semantics-preserving image transformations to the input image, and show how the resulting image sets can be used to estimate confidence in the classifier's prediction. We demonstrate the potential of our approach by extensively evaluating it on a wide variety of classifier architectures and datasets, including ResNext/ImageNet, achieving state of the art performance. This paper constitutes a significant revision of our earlier work in this direction (Bahat & Shakhnarovich, 2018).
