将现实留给想象：通过生成数据集实现鲁棒分类
Leaving Reality to Imagination: Robust Classification via Generated Datasets
AI总结：
研究生成数据集对图像分类器自然鲁棒性的影响，发现用基础生成模型生成的数据增强真实数据训练的ImageNet分类器，在自然分布偏移下比标准训练和微调模型生成数据具有更高的准确率和有效鲁棒性。
摘要：
近期关于鲁棒性的研究揭示了显著的性能差距：在类似于测试集的数据集上训练的神经图像分类器，与在自然分布偏移的数据（如训练期间观察到的物体类别的素描、绘画和动画）上训练的分类器之间存在差异。先前的工作主要通过设计训练数据的工程化增强，或通过对从互联网上抓取的海量野外训练数据集进行单个大模型的无监督预训练来缩小这一差距。然而，近年来数据集的概念也正在经历范式转变。随着现代生成模型在质量、易用性和可访问性方面的巨大提升，生成数据正充斥着网络。有鉴于此，我们研究以下问题：这些生成数据集如何影响图像分类器的自然鲁棒性？我们发现，在使用生成数据增强的真实数据上训练的 ImageNet 分类器，在面临自然分布偏移时，比标准训练和流行的增强策略实现了更高的准确率和有效鲁棒性。我们分析了影响这些结果的各种因素，包括条件策略的选择和生成数据的数量。此外，我们发现标准的 ImageNet 分类器在生成数据上的性能下降高达 20%，表明它们在准确分类具有新颖变化的物体时的脆弱性。最后，我们证明，与在真实数据增强的、由在真实数据上微调的生成模型生成的数据上训练的分类器相比，在由基础生成模型生成数据增强的真实数据上训练的图像分类器，对自然分布偏移表现出更强的抵抗力。代码、模型和数据集可在 https://github.com/Hritikbansal/generative-robustness 获取。
英文摘要：
Recent research on robustness has revealed significant performance gaps between neural image classifiers trained on datasets that are similar to the test set, and those that are from a naturally shifted distribution, such as sketches, paintings, and animations of the object categories observed during training. Prior work focuses on reducing this gap by designing engineered augmentations of training data or through unsupervised pretraining of a single large model on massive in-the-wild training datasets scraped from the Internet. However, the notion of a dataset is also undergoing a paradigm shift in recent years. With drastic improvements in the quality, ease-of-use, and access to modern generative models, generated data is pervading the web. In this light, we study the question: How do these generated datasets influence the natural robustness of image classifiers? We find that Imagenet classifiers trained on real data augmented with generated data achieve higher accuracy and effective robustness than standard training and popular augmentation strategies in the presence of natural distribution shifts. We analyze various factors influencing these results, including the choice of conditioning strategies and the amount of generated data. Additionally, we find that the standard ImageNet classifiers suffer a performance degradation of upto 20\% on the generated data, indicating their fragility at accurately classifying the objects under novel variations. Lastly, we demonstrate that the image classifiers, which have been trained on real data augmented with generated data from the base generative model, exhibit greater resilience to natural distribution shifts compared to the classifiers trained on real data augmented with generated data from the finetuned generative model on the real data. The code, models, and datasets are available at https://github.com/Hritikbansal/generative-robustness.
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。
