With the rise of Deep Neural Networks, machine learning systems are nowadays ubiquitous in a number of real-world applications, which bears the need for highly reliable models. This requires a thorough look not only at the accuracy of such systems, but also to their predictive uncertainty. Hence, we propose a novel technique (with two different variations, named M-ATTA and V-ATTA) based on test time augmentation, to improve the uncertainty calibration of deep models for image classification. Unlike other test time augmentation approaches, M/V-ATTA improves uncertainty calibration without affecting the model's accuracy, by leveraging an adaptive weighting system. We evaluate the performance of the technique with respect to different metrics of uncertainty calibration. Empirical results, obtained on CIFAR-10, CIFAR-100, as well as on the benchmark Aerial Image Dataset, indicate that the proposed approach outperforms state-of-the-art calibration techniques, while maintaining the baseline classification performance. Code for M/V-ATTA available at: https://github.com/pedrormconde/MV-ATTA.

翻译：随着深度神经网络的兴起，机器学习系统如今在众多现实应用中无处不在，这要求模型具备高度可靠性。这不仅需要关注此类系统的准确性，还需审视其预测不确定性。因此，我们提出一种基于测试时增强的新技术（包含两种变体，分别命名为M-ATTA和V-ATTA），用于改善深度模型在图像分类中的不确定性校准。与其他测试时增强方法不同，M/V-ATTA通过自适应加权系统，在不影响模型准确性的前提下提升了不确定性校准效果。我们使用不同不确定性校准指标评估了该技术的性能。在CIFAR-10、CIFAR-100以及基准航空影像数据集上的实证结果表明，所提方法在保持基线分类性能的同时，优于现有最先进的校准技术。M/V-ATTA的代码已开源在：https://github.com/pedrormconde/MV-ATTA。