Conference paper · 2021 · Open access

LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference

Benjamin Graham, Alaaeldin El-Nouby, Hugo Touvron, Pierre Stock, Armand Joulin, Hervé Jeǵou, Matthijs Douze

IEEE/CVF International Conference on Computer Vision (ICCV), 12239–12249 · Published 1 October 2021 · DOI 10.1109/iccv48922.2021.01204

Open PDFView at the publisherCite this paper

In brief

“LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference” is a 2021 conference paper by Benjamin Graham and 6 co-authors, published in IEEE/CVF International Conference on Computer Vision (ICCV). OpenAlex counts 1,373 citations as of 22 November 2026, which puts it in the top 1% of works published in 2021 by citations. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
1,373
Most cited in
2025 (348)
Field-weighted impact
50.15
References
71
Authors
7

Abstract

We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime. Our work exploits recent findings in attention-based architectures, which are competitive on highly parallel processing hardware. We revisit principles from the extensive literature on convolutional neural networks to apply them to transformers, in particular activation maps with decreasing resolutions. We also introduce the attention bias, a new way to integrate positional information in vision transformers.As a result, we propose LeViT: a hybrid neural network for fast inference image classification. We consider different measures of efficiency on different hardware platforms, so as to best reflect a wide range of application scenarios. Our extensive experiments empirically validate our technical choices and show they are suitable to most architectures. Overall, LeViT significantly outperforms existing convnets and vision transformers with respect to the speed/accuracy tradeoff. For example, at 80% ImageNet top-1 accuracy, LeViT is 5 times faster than EfficientNet on CPU. We release the code at https://github.com/facebookresearch/LeViT.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Graham, B., El-Nouby, A., Touvron, H., Stock, P., Joulin, A., Jeǵou, H., & Douze, M. (2021). LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference. IEEE/CVF International Conference on Computer Vision (ICCV), 12239–12249. https://doi.org/10.1109/iccv48922.2021.01204

MLA 9

Graham, Benjamin, et al. “LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference.” IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 12239–12249. https://doi.org/10.1109/iccv48922.2021.01204.

Chicago

Graham, Benjamin, Alaaeldin El-Nouby, Hugo Touvron, Pierre Stock, Armand Joulin, Hervé Jeǵou, and Matthijs Douze. 2021. “LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference.” IEEE/CVF International Conference on Computer Vision (ICCV): 12239–12249. https://doi.org/10.1109/iccv48922.2021.01204.

Harvard

Graham, B. et al. (2021) ‘LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference’, IEEE/CVF International Conference on Computer Vision (ICCV), pp. 12239–12249. doi:10.1109/iccv48922.2021.01204.

IEEE

B. Graham et al., “LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference,” IEEE/CVF International Conference on Computer Vision (ICCV), pp. 12239–12249, 2021, doi: 10.1109/iccv48922.2021.01204.

BibTeX

@inproceedings{graham2021levit,
  title     = {{LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference}},
  author    = {Graham, Benjamin and El-Nouby, Alaaeldin and Touvron, Hugo and Stock, Pierre and Joulin, Armand and Jeǵou, Hervé and Douze, Matthijs},
  booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
  year      = {2021},
  pages     = {12239--12249},
  doi       = {10.1109/iccv48922.2021.01204},
  url       = {https://doi.org/10.1109/iccv48922.2021.01204}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
20213636
2022187187
2023248248
2024323323
2025348348
2026231231

Its field-weighted citation impact is 50.15: it has been cited 50.15 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • vision transformer
  • fast inference
  • speed-accuracy trade-off
  • attentional bias
  • positional information
  • attention maps
  • image classification
  • efficient neural networks

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Graham, B., El-Nouby, A., Touvron, H., Stock, P., Joulin, A., Jeǵou, H., & Douze, M. (2021). LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference. IEEE/CVF International Conference on Computer Vision (ICCV), 12239–12249. https://doi.org/10.1109/iccv48922.2021.01204

How many times has this paper been cited?

1,373 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Benjamin Graham, Alaaeldin El-Nouby, Hugo Touvron, Pierre Stock, Armand Joulin, Hervé Jeǵou, Matthijs Douze.

What is the DOI of this paper?

10.1109/iccv48922.2021.01204, permanently at https://doi.org/10.1109/iccv48922.2021.01204. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.