We establish rigorous benchmarks for visual perception robustness. Synthetic images such as ImageNet-C, ImageNet-9, and Stylized ImageNet provide specific type of evaluation over synthetic corruptions, backgrounds, and textures, yet those robustness benchmarks are restricted in specified variations and have low synthetic quality. In this work, we introduce generative model as a data source for synthesizing hard images that benchmark deep models' robustness. Leveraging diffusion models, we are able to generate images with more diversified backgrounds, textures, and materials than any prior work, where we term this benchmark as ImageNet-D. Experimental results show that ImageNet-D results in a significant accuracy drop to a range of vision models, from the standard ResNet visual classifier to the latest foundation models like CLIP and MiniGPT-4, significantly reducing their accuracy by up to 60\%. Our work suggests that diffusion models can be an effective source to test vision models. The code and dataset are available at https://github.com/chenshuang-zhang/imagenet_d.

翻译：我们建立了视觉感知鲁棒性的严格基准。诸如ImageNet-C、ImageNet-9和Stylized ImageNet等合成图像提供了针对合成扰动、背景和纹理的特定类型评估，但这些鲁棒性基准受限于特定变化且合成质量较低。在本工作中，我们引入生成模型作为合成困难图像的数据源，以评测深度模型的鲁棒性。利用扩散模型，我们能够生成比先前研究具有更多样化背景、纹理和材质的图像，并将此基准命名为ImageNet-D。实验结果表明，ImageNet-D导致一系列视觉模型（从标准ResNet视觉分类器到最新的基础模型如CLIP和MiniGPT-4）的准确率显著下降，最高降幅达60%。我们的研究表明，扩散模型可以成为测试视觉模型的有效数据源。相关代码和数据集可从https://github.com/chenshuang-zhang/imagenet_d获取。