Preprint · 2022 · Open access

Vision Transformers in 2022: An Update on Tiny ImageNet

Ethan Huynh

arXiv (Cornell University) · Published 21 May 2022 · DOI 10.48550/arxiv.2205.10660

Open PDFView at the publisherCite this paper

In brief

“Vision Transformers in 2022: An Update on Tiny ImageNet” is a 2022 preprint by Ethan Huynh, published in arXiv (Cornell University). OpenAlex counts 26 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
26
Most cited in
2023 (10)
References
17
Authors
1

Abstract

The recent advances in image transformers have shown impressive results and have largely closed the gap between traditional CNN architectures. The standard procedure is to train on large datasets like ImageNet-21k and then finetune on ImageNet-1k. After finetuning, researches will often consider the transfer learning performance on smaller datasets such as CIFAR-10/100 but have left out Tiny ImageNet. This paper offers an update on vision transformers' performance on Tiny ImageNet. I include Vision Transformer (ViT) , Data Efficient Image Transformer (DeiT), Class Attention in Image Transformer (CaiT), and Swin Transformers. In addition, Swin Transformers beats the current state-of-the-art result with a validation accuracy of 91.35%. Code is available here: https://github.com/ehuynh1106/TinyImageNet-Transformers

Cite this paper

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

APA 7

Huynh, E. (2022). Vision Transformers in 2022: An Update on Tiny ImageNet. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2205.10660

MLA 9

Huynh, Ethan. “Vision Transformers in 2022: An Update on Tiny ImageNet.” arXiv (Cornell University), 2022. https://doi.org/10.48550/arxiv.2205.10660.

Chicago

Huynh, Ethan. 2022. “Vision Transformers in 2022: An Update on Tiny ImageNet.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2205.10660.

Harvard

Huynh, E. (2022) ‘Vision Transformers in 2022: An Update on Tiny ImageNet’, arXiv (Cornell University). doi:10.48550/arxiv.2205.10660.

IEEE

E. Huynh, “Vision Transformers in 2022: An Update on Tiny ImageNet,” arXiv (Cornell University), 2022, doi: 10.48550/arxiv.2205.10660.

BibTeX

@misc{huynh2022vision,
  title     = {{Vision Transformers in 2022: An Update on Tiny ImageNet}},
  author    = {Huynh, Ethan},
  howpublished = {arXiv (Cornell University)},
  year      = {2022},
  doi       = {10.48550/arxiv.2205.10660},
  url       = {https://doi.org/10.48550/arxiv.2205.10660}
}

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

Citations by year

YearCitationsShare of the best year
20231010
202433
202588
202655

Topic and keywords

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

  • vision transformer
  • Tiny ImageNet
  • transfer learning
  • Swin Transformer
  • DeiT
  • image classification
  • small image datasets

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?

Huynh, E. (2022). Vision Transformers in 2022: An Update on Tiny ImageNet. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2205.10660

How many times has this paper been cited?

26 times, according to OpenAlex on 18 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?

Ethan Huynh.

What is the DOI of this paper?

10.48550/arxiv.2205.10660, permanently at https://doi.org/10.48550/arxiv.2205.10660. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 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.