从雪到雨：评估基于模型的鲁棒训练的鲁棒性、校准和复杂性
From Snow to Rain: Evaluating Robustness, Calibration, and Complexity of Model-Based Robust Training
AI总结：
本文研究了基于模型的鲁棒训练方法，通过学习噪声变化模型生成真实腐蚀，实验表明该方法在不同腐蚀强度下表现更优，且在计算成本较低的情况下仍能保持鲁棒性。
摘要：
对自然腐蚀的鲁棒性仍然是可靠深度学习的关键挑战，特别是在安全敏感领域。我们研究了一种基于模型的训练方法，利用学习的噪声变化模型生成逼真的腐蚀，以及新的混合策略，结合随机覆盖与对抗性细化在噪声空间中。使用具有雪和雨腐蚀的挑战性真实和现实环境交通标志识别数据集（CURE-TSR），我们评估了在不同腐蚀严重程度下的准确性、校准和训练复杂性。我们的结果表明，基于模型的方法在Vanilla、对抗训练和AugMix基线中始终表现更优，基于模型的对抗训练在所有腐蚀下提供了最强的鲁棒性，但以更高的计算成本为代价。而基于模型的数据增强在T更低的计算复杂性下实现了相当的鲁棒性，且未导致统计上显著的性能下降。这些发现突显了学习噪声模型在捕捉自然变化中的重要性，并表明了在挑战性条件下更健壮和校准模型的有希望路径。
英文摘要：
Robustness to natural corruptions remains a critical challenge for reliable deep learning, particularly in safety-sensitive domains. We study a family of model-based training approaches that leverage a learned nuisance variation model to generate realistic corruptions, as well as new hybrid strategies that combine random coverage with adversarial refinement in nuisance space. Using the Challenging Unreal and Real Environments for Traffic Sign Recognition dataset (CURE-TSR), with Snow and Rain corruptions, we evaluate accuracy, calibration, and training complexity across corruption severities. Our results show that model-based methods consistently outperform baselines Vanilla, Adversarial Training, and AugMix baselines, with model-based adversarial training providing the strongest robustness under across all corruptions but at the expense of higher computation and model-based data augmentation achieving comparable robustness with $T$ less computational complexity without incurring a statistically significant drop in performance. These findings highlight the importance of learned nuisance models for capturing natural variability, and suggest a promising path toward more resilient and calibrated models under challenging conditions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
