# ImageNet-22k Pretrained

FocalNet is an image classification model based on the focal modulation network, pretrained by the Microsoft team on the ImageNet-22k dataset.

CvT-21 is a vision model combining convolutional and Transformer architectures, pretrained on ImageNet-22k and fine-tuned on ImageNet-1k

ConvNeXT is a pure convolutional model inspired by the design of vision Transformers, trained on the ImageNet-22k dataset, with performance surpassing Transformers.

ConvNeXT is a pure convolutional model inspired by vision Transformer designs, pretrained on ImageNet-22k and fine-tuned on ImageNet-1k, outperforming Transformers.