论文标题
深度学习图像分类中数据和特定于类的不确定性估计的测试时间混合增加
Test-Time Mixup Augmentation for Data and Class-Specific Uncertainty Estimation in Deep Learning Image Classification
论文作者
论文摘要
对训练的深度学习网络的不确定性估计对于优化学习效率和评估网络预测的可靠性非常有价值。在本文中，我们提出了一种使用测试时间混合增强（TTMA）估算深度学习图像分类不确定性的方法。为了提高现有不确定性中正确和不正确预测的能力，我们通过应用混合增强来测试数据并测量预测标签直方图的熵来引入TTMA数据不确定性（TTMA-DU）。除TTMA-DU外，我们还提出了TTMA类别特异性不确定性（TTMA-CSU），该不确定性（TTMA-CSU）捕获了特定于单个类别的差异不确定性，并洞悉了训练有素的网络中的类别混乱和类相似性。我们验证了有关ISIC-18皮肤病变诊断数据集和CIFAR-100现实世界图像分类数据集的建议方法。我们的实验表明，（1）TTMA-DU更有效地区分了与由于混合扰动引起的现有不确定性度量的正确和错误的预测，并且（2）TTMA-CSU提供了有关两个数据集的类混淆和类相似性的信息。
Uncertainty estimation of trained deep learning networks is valuable for optimizing learning efficiency and evaluating the reliability of network predictions. In this paper, we propose a method for estimating uncertainty in deep learning image classification using test-time mixup augmentation (TTMA). To improve the ability to distinguish correct and incorrect predictions in existing aleatoric uncertainty, we introduce TTMA data uncertainty (TTMA-DU) by applying mixup augmentation to test data and measuring the entropy of the predicted label histogram. In addition to TTMA-DU, we propose TTMA class-specific uncertainty (TTMA-CSU), which captures aleatoric uncertainty specific to individual classes and provides insight into class confusion and class similarity within the trained network. We validate our proposed methods on the ISIC-18 skin lesion diagnosis dataset and the CIFAR-100 real-world image classification dataset. Our experiments show that (1) TTMA-DU more effectively differentiates correct and incorrect predictions compared to existing uncertainty measures due to mixup perturbation, and (2) TTMA-CSU provides information on class confusion and class similarity for both datasets.
