An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale¶

Abstract¶

While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of data and transferred to multiple mid-sized or small image recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc.), Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.

Citation¶

@inproceedings{
  dosovitskiy2021an,
  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
  author={Alexey Dosovitskiy and Lucas Beyer and Alexander Kolesnikov and Dirk Weissenborn and Xiaohua Zhai and Thomas Unterthiner and Mostafa Dehghani and Matthias Minderer and Georg Heigold and Sylvain Gelly and Jakob Uszkoreit and Neil Houlsby},
  booktitle={International Conference on Learning Representations},
  year={2021},
  url={https://openreview.net/forum?id=YicbFdNTTy}
}

The training step of Vision Transformers is divided into two steps. The first step is training the model on a large dataset, like ImageNet-21k, and get the pretrain model. And the second step is training the model on the target dataset, like ImageNet-1k, and get the finetune model. Here, we provide both pretrain models and finetune models.

Pretrain model¶

The pre-trained models are converted from model zoo of Google Research.

ImageNet 21k¶

Model	Params(M)	Flops(G)	Download
ViT-B16*	86.86	33.03	model
ViT-B32*	88.30	8.56	model
ViT-L16*	304.72	116.68	model

Models with * are converted from other repos.

Finetune model¶

The finetune models are converted from model zoo of Google Research.

ImageNet 1k¶

Model	Pretrain	resolution	Params(M)	Flops(G)	Top-1 (%)	Top-5 (%)	Config	Download
ViT-B16*	ImageNet-21k	384x384	86.86	33.03	85.43	97.77	config	model
ViT-B32*	ImageNet-21k	384x384	88.30	8.56	84.01	97.08	config	model
ViT-L16*	ImageNet-21k	384x384	304.72	116.68	85.63	97.63	config	model

Models with * are converted from other repos.