ImageNet-D

Introduced 2024-03-27

ImageNet-D contains 4835 test images featuring diverse backgrounds (3,764), textures (498), and materials (573). Generated by diffusion models, ImageNet-D achieves superior image fidelity and collection efficiency than prior studies. Evaluation 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%.

Related Benchmarks

Imagenet-dog-15/Image Clustering/ARI Imagenet-dog-15/Image Clustering/Accuracy Imagenet-dog-15/Image Clustering/Backbone Imagenet-dog-15/Image Clustering/Image Size Imagenet-dog-15/Image Clustering/NMI