Conference paper · 2021 · Open access
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
IEEE/CVF International Conference on Computer Vision (ICCV), 538–547 · Published 1 October 2021 · DOI 10.1109/iccv48922.2021.00060
In brief
“Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet” is a 2021 conference paper by Li Yuan and 8 co-authors, published in IEEE/CVF International Conference on Computer Vision (ICCV). OpenAlex counts 3,164 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
- 3,164
- Most cited in
- 2023 (722)
- Field-weighted impact
- 132.73
- References
- 66
- Authors
- 9
Abstract
Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed length and then applies multiple Transformer layers to model their global relation for classification. However, ViT achieves inferior performance to CNNs when trained from scratch on a midsize dataset like ImageNet. We find it is because: 1) the simple tokenization of input images fails to model the important local structure such as edges and lines among neighboring pixels, leading to low training sample efficiency; 2) the redundant attention backbone design of ViT leads to limited feature richness for fixed computation budgets and limited training samples. To overcome such limitations, we propose a new Tokens-To-Token Vision Transformer (T2T-VTT), which incorporates 1) a layer-wise Tokens-to-Token (T2T) transformation to progressively structurize the image to tokens by recursively aggregating neighboring Tokens into one Token (Tokens-to-Token), such that local structure represented by surrounding tokens can be modeled and tokens length can be reduced; 2) an efficient backbone with a deep-narrow structure for vision transformer motivated by CNN architecture design after empirical study. Notably, T2T-ViT reduces the parameter count and MACs of vanilla ViT by half, while achieving more than 3.0% improvement when trained from scratch on ImageNet. It also outperforms ResNets and achieves comparable performance with MobileNets by directly training on ImageNet. For example, T2T-ViT with comparable size to ResNet50 (21.5M parameters) can achieve 83.3% top1 accuracy in image resolution 384x384 on ImageNet.1
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F. E. H., Feng, J., & Yan, S. (2021). Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet. IEEE/CVF International Conference on Computer Vision (ICCV), 538–547. https://doi.org/10.1109/iccv48922.2021.00060
MLA 9
Yuan, Li, et al. “Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet.” IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 538–547. https://doi.org/10.1109/iccv48922.2021.00060.
Chicago
Yuan, Li, Yunpeng Chen, Tao Wang, Weihao Yu, Yujun Shi, Zihang Jiang, Francis E. H. Tay, Jiashi Feng, and Shuicheng Yan. 2021. “Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet.” IEEE/CVF International Conference on Computer Vision (ICCV): 538–547. https://doi.org/10.1109/iccv48922.2021.00060.
Harvard
Yuan, L. et al. (2021) ‘Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet’, IEEE/CVF International Conference on Computer Vision (ICCV), pp. 538–547. doi:10.1109/iccv48922.2021.00060.
IEEE
L. Yuan et al., “Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet,” IEEE/CVF International Conference on Computer Vision (ICCV), pp. 538–547, 2021, doi: 10.1109/iccv48922.2021.00060.
BibTeX
@inproceedings{yuan2021tokens,
title = {{Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet}},
author = {Yuan, Li and Chen, Yunpeng and Wang, Tao and Yu, Weihao and Shi, Yujun and Jiang, Zihang and Tay, Francis E. H. and Feng, Jiashi and Yan, Shuicheng},
booktitle = {IEEE/CVF International Conference on Computer Vision (ICCV)},
year = {2021},
pages = {538--547},
doi = {10.1109/iccv48922.2021.00060},
url = {https://doi.org/10.1109/iccv48922.2021.00060}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2021 | 152 | |
| 2022 | 515 | |
| 2023 | 722 | |
| 2024 | 665 | |
| 2025 | 699 | |
| 2026 | 411 |
Its field-weighted citation impact is 132.73: it has been cited 132.73 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
- image classification
- tokenization
- training from scratch
- ImageNet
- parameter efficiency
- attention mechanism
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F. E. H., Feng, J., & Yan, S. (2021). Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet. IEEE/CVF International Conference on Computer Vision (ICCV), 538–547. https://doi.org/10.1109/iccv48922.2021.00060
How many times has this paper been cited?
3,164 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?
Li Yuan, Yunpeng Chen, Tao Wang, Weihao Yu, Yujun Shi, Zihang Jiang, Francis E. H. Tay, Jiashi Feng, Shuicheng Yan.
What is the DOI of this paper?
10.1109/iccv48922.2021.00060, permanently at https://doi.org/10.1109/iccv48922.2021.00060. 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.