Although Convolutional Neural Networks (CNNs) have high accuracy in image recognition, they are vulnerable to adversarial examples and out-of-distribution data, and the difference from human recognition has been pointed out. In order to improve the robustness against out-of-distribution data, we present a frequency-based data augmentation technique that replaces the frequency components with other images of the same class. When the training data are CIFAR10 and the out-of-distribution data are SVHN, the Area Under Receiver Operating Characteristic (AUROC) curve of the model trained with the proposed method increases from 89.22\% to 98.15\%, and further increased to 98.59\% when combined with another data augmentation method. Furthermore, we experimentally demonstrate that the robust model for out-of-distribution data uses a lot of high-frequency components of the image.
翻译:虽然进化神经网络(CNNs)在图像识别方面具有很高的准确性,但它们容易受到对抗性实例和分配外数据的影响,而且已经指出与人类认知的差异。为了提高对分配外数据的稳健性,我们提出了一种基于频率的数据增强技术,用同一类的其他图像取代频率组成部分。当培训数据为CIFAR10, 分配外数据为SVHN时,经过拟议方法培训的模型“接收者业务特征区域”曲线从89.22 ⁇ ==98.15 ⁇ 增至98.15 ⁇,并在与另一种数据增强方法相结合时进一步增至98.59 ⁇ 。此外,我们实验性地证明,强大的数据分配外数据模型使用了图像的许多高频组成部分。