Distribution shifts, which often occur in the real world, degrade the accuracy of deep learning systems, and thus improving robustness to distribution shifts is essential for practical applications. To improve robustness, we study an image enhancement method that generates recognition-friendly images without retraining the recognition model. We propose a novel image enhancement method, DynTTA, which is based on differentiable data augmentation techniques and generates a blended image from many augmented images to improve the recognition accuracy under distribution shifts. In addition to standard data augmentations, DynTTA also incorporates deep neural network-based image transformation, further improving the robustness. Because DynTTA is composed of differentiable functions, it can be directly trained with the classification loss of the recognition model. In experiments with widely used image recognition datasets using various classification models, DynTTA improves the robustness with almost no reduction in classification accuracy for clean images, thus outperforming the existing methods. Furthermore, the results show that robustness is significantly improved by estimating the training-time augmentations for distribution-shifted datasets using DynTTA and retraining the recognition model with the estimated augmentations. DynTTA is a promising approach for applications that require both clean accuracy and robustness. Our code is available at \url{https://github.com/s-enmt/DynTTA}.

翻译：现实世界中经常出现的分布偏移会降低深度学习系统的准确性，因此提高对分布偏移的鲁棒性对于实际应用至关重要。为增强鲁棒性，我们研究了一种无需重新训练识别模型即可生成利于识别的图像的图像增强方法。我们提出了一种新颖的图像增强方法DynTTA，该方法基于可微数据增强技术，通过融合多张增强图像生成混合图像，以提高分布偏移下的识别准确率。除标准数据增强外，DynTTA还结合了基于深度神经网络的图像变换，进一步提升了鲁棒性。由于DynTTA由可微函数构成，可直接通过识别模型的分类损失进行训练。在使用多种分类模型对广泛使用的图像识别数据集进行的实验中，DynTTA在几乎不降低干净图像分类精度的前提下显著提升了鲁棒性，其性能优于现有方法。此外，实验结果表明：通过使用DynTTA估计分布偏移数据集的训练时增强策略，并利用估计出的增强方式重新训练识别模型，能显著提升系统鲁棒性。DynTTA为同时要求干净图像精度与鲁棒性的应用场景提供了有前景的解决方案。代码已开源：\url{https://github.com/s-enmt/DynTTA}。