Conference paper · 2021 · Open access

CvT: Introducing Convolutions to Vision Transformers

Haiping Wu, Bin Xiao, Noel Codella, Mengchen Liu, Xiyang Dai, Lu Yuan, Lei Zhang

IEEE/CVF International Conference on Computer Vision (ICCV), 22–31 · Published 1 October 2021 · DOI 10.1109/iccv48922.2021.00009

Open PDFView at the publisherCite this paper

In brief

“CvT: Introducing Convolutions to Vision Transformers” is a 2021 conference paper by Haiping Wu and 6 co-authors, published in IEEE/CVF International Conference on Computer Vision (ICCV). OpenAlex counts 3,406 citations as of 22 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
3,406
Most cited in
2024 (841)
Field-weighted impact
141.24
References
50
Authors
7

Abstract

We present in this paper a new architecture, named Convolutional vision Transformer (CvT), that improves Vision Transformer (ViT) in performance and efficiency by introducing convolutions into ViT to yield the best of both de-signs. This is accomplished through two primary modifications: a hierarchy of Transformers containing a new convolutional token embedding, and a convolutional Transformer block leveraging a convolutional projection. These changes introduce desirable properties of convolutional neural networks (CNNs) to the ViT architecture (i.e. shift, scale, and distortion invariance) while maintaining the merits of Transformers (i.e. dynamic attention, global context, and better generalization). We validate CvT by conducting extensive experiments, showing that this approach achieves state-of-the-art performance over other Vision Transformers and ResNets on ImageNet-1k, with fewer parameters and lower FLOPs. In addition, performance gains are maintained when pretrained on larger datasets (e.g. ImageNet-22k) and fine-tuned to downstream tasks. Pretrained on ImageNet-22k, our CvT-W24 obtains a top-1 accuracy of 87.7% on the ImageNet-1k val set. Finally, our results show that the positional encoding, a crucial component in existing Vision Transformers, can be safely re-moved in our model, simplifying the design for higher resolution vision tasks. Code will be released at https://github.com/microsoft/CvT.

Cite this paper

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

APA 7

Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., & Zhang, L. (2021). CvT: Introducing Convolutions to Vision Transformers. IEEE/CVF International Conference on Computer Vision (ICCV), 22–31. https://doi.org/10.1109/iccv48922.2021.00009

MLA 9

Wu, Haiping, et al. “CvT: Introducing Convolutions to Vision Transformers.” IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 22–31. https://doi.org/10.1109/iccv48922.2021.00009.

Chicago

Wu, Haiping, Bin Xiao, Noel Codella, Mengchen Liu, Xiyang Dai, Lu Yuan, and Lei Zhang. 2021. “CvT: Introducing Convolutions to Vision Transformers.” IEEE/CVF International Conference on Computer Vision (ICCV): 22–31. https://doi.org/10.1109/iccv48922.2021.00009.

Harvard

Wu, H. et al. (2021) ‘CvT: Introducing Convolutions to Vision Transformers’, IEEE/CVF International Conference on Computer Vision (ICCV), pp. 22–31. doi:10.1109/iccv48922.2021.00009.

IEEE

H. Wu et al., “CvT: Introducing Convolutions to Vision Transformers,” IEEE/CVF International Conference on Computer Vision (ICCV), pp. 22–31, 2021, doi: 10.1109/iccv48922.2021.00009.

BibTeX

@inproceedings{wu2021introducing,
  title     = {{CvT: Introducing Convolutions to Vision Transformers}},
  author    = {Wu, Haiping and Xiao, Bin and Codella, Noel and Liu, Mengchen and Dai, Xiyang and Yuan, Lu and Zhang, Lei},
  booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
  year      = {2021},
  pages     = {22--31},
  doi       = {10.1109/iccv48922.2021.00009},
  url       = {https://doi.org/10.1109/iccv48922.2021.00009}
}

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

Citations by year

YearCitationsShare of the best year
201311
2021111111
2022490490
2023730730
2024841841
2025724724
2026509509

Its field-weighted citation impact is 141.24: it has been cited 141.24 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

  • convolutional vision transformer
  • vision transformer
  • CNN-Transformer hybrid
  • ImageNet-1K
  • parameter efficiency

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?

Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., & Zhang, L. (2021). CvT: Introducing Convolutions to Vision Transformers. IEEE/CVF International Conference on Computer Vision (ICCV), 22–31. https://doi.org/10.1109/iccv48922.2021.00009

How many times has this paper been cited?

3,406 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?

Haiping Wu, Bin Xiao, Noel Codella, Mengchen Liu, Xiyang Dai, Lu Yuan, Lei Zhang.

What is the DOI of this paper?

10.1109/iccv48922.2021.00009, permanently at https://doi.org/10.1109/iccv48922.2021.00009. 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.