They | |
outperform both the original model (ViT) as well as Data-efficient Image Transformers (DeiT) when fine-tuned on ImageNet-1K and CIFAR-100. |
They | |
outperform both the original model (ViT) as well as Data-efficient Image Transformers (DeiT) when fine-tuned on ImageNet-1K and CIFAR-100. |