Deep Learning (DL) models achieve great successes in many domains. However, DL models increasingly face safety and robustness concerns, including noisy labeling in the training stage and feature distribution shifts in the testing stage. Previous works made significant progress in addressing these problems, but the focus has largely been on developing solutions for only one problem at a time. For example, recent work has argued for the use of tunable robust loss functions to mitigate label noise, and data augmentation (e.g., AugMix) to combat distribution shifts. As a step towards addressing both problems simultaneously, we introduce AugLoss, a simple but effective methodology that achieves robustness against both train-time noisy labeling and test-time feature distribution shifts by unifying data augmentation and robust loss functions. We conduct comprehensive experiments in varied settings of real-world dataset corruption to showcase the gains achieved by AugLoss compared to previous state-of-the-art methods. Lastly, we hope this work will open new directions for designing more robust and reliable DL models under real-world corruptions.

翻译：深度学习（DL）模型在许多领域取得了巨大成功。然而，DL模型日益面临安全性和鲁棒性问题，包括训练阶段的噪声标签和测试阶段的特征分布偏移。先前研究在解决这些问题上取得了显著进展，但重点主要集中于针对单一问题开发解决方案。例如，近期工作提出使用可调节的鲁棒损失函数来缓解标签噪声，以及通过数据增强（如AugMix）应对分布偏移。为同时解决这两个问题，我们提出了AugLoss——一种简单而有效的方法，通过统一数据增强与鲁棒损失函数，实现对训练期噪声标签和测试期特征分布偏移的双重鲁棒性。我们在多种真实数据集污染的设定下进行了综合实验，展示了AugLoss相较于先前最先进方法的性能提升。最后，我们希望此项工作能为设计更鲁棒、更可靠的DL模型以应对真实世界的污染开辟新方向。