Data augmentation has been proven effective for training high-accuracy convolutional neural network classifiers by preventing overfitting. However, building deep neural networks in real-world scenarios requires not only high accuracy on clean data but also robustness when data distributions shift. While prior methods have proposed that there is a trade-off between accuracy and robustness, we propose IPMix, a simple data augmentation approach to improve robustness without hurting clean accuracy. IPMix integrates three levels of data augmentation (image-level, patch-level, and pixel-level) into a coherent and label-preserving technique to increase the diversity of training data with limited computational overhead. To further improve the robustness, IPMix introduces structural complexity at different levels to generate more diverse images and adopts the random mixing method for multi-scale information fusion. Experiments demonstrate that IPMix outperforms state-of-the-art corruption robustness on CIFAR-C and ImageNet-C. In addition, we show that IPMix also significantly improves the other safety measures, including robustness to adversarial perturbations, calibration, prediction consistency, and anomaly detection, achieving state-of-the-art or comparable results on several benchmarks, including ImageNet-R, ImageNet-A, and ImageNet-O.

翻译：数据增强已被证明通过防止过拟合，可有效提升卷积神经网络分类器的准确率。然而，在现实场景中构建深度神经网络不仅需要在干净数据上达到高准确率，还需应对数据分布偏移时的鲁棒性。尽管先前方法认为准确率与鲁棒性之间存在权衡，我们提出的IPMix作为一种简洁的数据增强方法，可在不降低干净数据准确率的前提下提升鲁棒性。IPMix将图像级、图像块级和像素级三个层次的数据增强整合为连贯且保持标签的技术，以有限的计算开销提升训练数据多样性。为进一步增强鲁棒性，IPMix通过在不同层级引入结构复杂性生成更多样化的图像，并采用随机混合方法实现多尺度信息融合。实验表明，IPMix在CIFAR-C和ImageNet-C基准测试上达到最先进的污染鲁棒性能。此外，我们证明IPMix还能显著提升其他安全指标，包括对抗扰动鲁棒性、校准能力、预测一致性和异常检测性能，在ImageNet-R、ImageNet-A和ImageNet-O等多个基准测试中取得最先进或可比结果。