# DeiT¶

## Abstract¶

Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. However, these visual transformers are pre-trained with hundreds of millions of images using an expensive infrastructure, thereby limiting their adoption. In this work, we produce a competitive convolution-free transformer by training on Imagenet only. We train them on a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop evaluation) on ImageNet with no external data. More importantly, we introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention. We show the interest of this token-based distillation, especially when using a convnet as a teacher. This leads us to report results competitive with convnets for both Imagenet (where we obtain up to 85.2% accuracy) and when transferring to other tasks. We share our code and models.

## Results and models¶

### ImageNet-1k¶

The teacher of the distilled version DeiT is RegNetY-16GF.

Model

Pretrain

Params(M)

Flops(G)

Top-1 (%)

Top-5 (%)

Config

DeiT-tiny

From scratch

5.72

1.08

74.50

92.24

config

DeiT-tiny distilled*

From scratch

5.72

1.08

74.51

91.90

config

model

DeiT-small

From scratch

22.05

4.24

80.69

95.06

config

DeiT-small distilled*

From scratch

22.05

4.24

81.17

95.40

config

model

DeiT-base

From scratch

86.57

16.86

81.76

95.81

config

DeiT-base*

From scratch

86.57

16.86

81.79

95.59

config

model

DeiT-base distilled*

From scratch

86.57

16.86

83.33

96.49

config

model

DeiT-base 384px*

ImageNet-1k

86.86

49.37

83.04

96.31

config

model

DeiT-base distilled 384px*

ImageNet-1k

86.86

49.37

85.55

97.35

config

model

Models with * are converted from the official repo. The config files of these models are only for validation. We don’t ensure these config files’ training accuracy and welcome you to contribute your reproduction results.

Warning

MMClassification doesn’t support training the distilled version DeiT. And we provide distilled version checkpoints for inference only.

## Citation¶

@InProceedings{pmlr-v139-touvron21a,
title =     {Training data-efficient image transformers &amp; distillation through attention},
author =    {Touvron, Hugo and Cord, Matthieu and Douze, Matthijs and Massa, Francisco and Sablayrolles, Alexandre and Jegou, Herve},
booktitle = {International Conference on Machine Learning},
pages =     {10347--10357},
year =      {2021},
volume =    {139},
month =     {July}
}